Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 731 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1179. Min Range: -3.1179
Max Act: 3.1179. Min Act: -0.1700
Data Index: 8284957 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1179. Min Range: -3.1179
Max Act: 3.1021. Min Act: -0.1700
Data Index: 5156793 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1179. Min Range: -3.1179
Max Act: 3.1021. Min Act: -0.1700
Data Index: 3644403 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1179. Min Range: -3.1179
Max Act: 3.0548. Min Act: -0.1700
Data Index: 308574 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1179. Min Range: -3.1179
Max Act: 3.0074. Min Act: -0.1700
Data Index: 7438065 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9758. Min Act: -0.1700
Data Index: 7392237 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9758. Min Act: -0.1700
Data Index: 7438059 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9600. Min Act: -0.1700
Data Index: 6884335 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9600. Min Act: -0.1700
Data Index: 1540299 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9442. Min Act: -0.1700
Data Index: 6501611 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 5519641 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 5453888 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 3820923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 2676891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 2208851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 6581716 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 8576001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9283. Min Act: -0.1700
Data Index: 2524384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.9125. Min Act: -0.1700
Data Index: 4338911 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1179. Min Range: -3.1179
Max Act: 2.8808. Min Act: -0.1700
Data Index: 3404680 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19