Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0653. Min Range: -12.0653
Max Act: 12.0653. Min Act: -0.1700
Data Index: 8361452 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.6903. Min Act: -0.1700
Data Index: 6475118 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.3153. Min Act: -0.1700
Data Index: 6839655 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.0653. Min Act: -0.1700
Data Index: 4128231 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.0028. Min Act: -0.1700
Data Index: 6475119 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.0028. Min Act: -0.1700
Data Index: 2636890 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.0028. Min Act: -0.1700
Data Index: 6207252 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.9403. Min Act: -0.1700
Data Index: 1583428 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0653. Min Range: -12.0653
Max Act: 11.0028. Min Act: -0.1700
Data Index: 4515410 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.9403. Min Act: -0.1700
Data Index: 6670555 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.9403. Min Act: -0.1700
Data Index: 3721818 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.9403. Min Act: -0.1700
Data Index: 7902928 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.8778. Min Act: -0.1700
Data Index: 8801540 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.8778. Min Act: -0.1700
Data Index: 3488117 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.8153. Min Act: -0.1700
Data Index: 7453295 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.8153. Min Act: -0.1700
Data Index: 2229620 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.8153. Min Act: -0.1700
Data Index: 5219741 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.7528. Min Act: -0.1700
Data Index: 1115658 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.6903. Min Act: -0.1700
Data Index: 3193208 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0653. Min Range: -12.0653
Max Act: 10.6903. Min Act: -0.1700
Data Index: 8353970 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19