Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2437. Min Range: -8.2437
Max Act: 8.2437. Min Act: -0.1700
Data Index: 3724069 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2437. Min Range: -8.2437
Max Act: 8.0874. Min Act: -0.1700
Data Index: 6568959 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.8999. Min Act: -0.1700
Data Index: 3150700 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.8999. Min Act: -0.1700
Data Index: 1651140 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.8374. Min Act: -0.1700
Data Index: 3422834 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.8062. Min Act: -0.1700
Data Index: 2513445 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7749. Min Act: -0.1700
Data Index: 5798525 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7749. Min Act: -0.1700
Data Index: 8093796 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7749. Min Act: -0.1700
Data Index: 7280248 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7749. Min Act: -0.1700
Data Index: 5104256 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7749. Min Act: -0.1700
Data Index: 7777974 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7437. Min Act: -0.1700
Data Index: 1130999 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7437. Min Act: -0.1700
Data Index: 7059942 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7437. Min Act: -0.1700
Data Index: 8589579 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7437. Min Act: -0.1700
Data Index: 5259964 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7124. Min Act: -0.1700
Data Index: 995626 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.7124. Min Act: -0.1700
Data Index: 2122396 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.6812. Min Act: -0.1700
Data Index: 6337158 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.6499. Min Act: -0.1700
Data Index: 7661611 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2437. Min Range: -8.2437
Max Act: 7.6812. Min Act: -0.1700
Data Index: 4416167 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19