Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.8939. Min Act: -0.1700
Data Index: 4747062 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.6752. Min Act: -0.1700
Data Index: 1170421 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.6752. Min Act: -0.1700
Data Index: 5411061 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.6127. Min Act: -0.1700
Data Index: 4362202 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.6127. Min Act: -0.1700
Data Index: 8131941 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.5814. Min Act: -0.1700
Data Index: 4651058 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.5189. Min Act: -0.1700
Data Index: 8758464 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.4877. Min Act: -0.1700
Data Index: 2618144 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3627. Min Act: -0.1700
Data Index: 2778192 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3314. Min Act: -0.1700
Data Index: 2523099 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3314. Min Act: -0.1700
Data Index: 7930782 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.2689. Min Act: -0.1700
Data Index: 1349046 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3002. Min Act: -0.1700
Data Index: 3895443 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.2377. Min Act: -0.1700
Data Index: 1186415 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.2377. Min Act: -0.1700
Data Index: 2099425 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1752. Min Act: -0.1700
Data Index: 2325903 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1439. Min Act: -0.1700
Data Index: 6394118 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1127. Min Act: -0.1700
Data Index: 7913977 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1127. Min Act: -0.1700
Data Index: 205345 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1127. Min Act: -0.1700
Data Index: 1727279 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19