Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5903 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.9987. Min Act: -0.1700
Data Index: 5131502 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0612. Min Range: -10.0612
Max Act: 10.0612. Min Act: -0.1700
Data Index: 595283 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.6862. Min Act: -0.1700
Data Index: 1799620 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.4987. Min Act: -0.1700
Data Index: 2100231 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.4362. Min Act: -0.1700
Data Index: 5919772 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.3737. Min Act: -0.1700
Data Index: 4714600 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.3737. Min Act: -0.1700
Data Index: 2082298 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 311119 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 3538233 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 6873692 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0612. Min Range: -10.0612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 7800765 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.9987. Min Act: -0.1700
Data Index: 6423784 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.9987. Min Act: -0.1700
Data Index: 8440824 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 5619313 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 5833837 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.9362. Min Act: -0.1700
Data Index: 1483426 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 6852319 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 1493900 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 632674 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0612. Min Range: -10.0612
Max Act: 8.8737. Min Act: -0.1700
Data Index: 2141232 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19