Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 381 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.9131. Min Act: -0.1700
Data Index: 8219139 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8818. Min Act: -0.1700
Data Index: 7578868 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8506. Min Act: -0.1700
Data Index: 6043561 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8818. Min Act: -0.1700
Data Index: 8025193 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8818. Min Act: -0.1700
Data Index: 8025185 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8506. Min Act: -0.1700
Data Index: 6826008 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8193. Min Act: -0.1700
Data Index: 5314694 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8193. Min Act: -0.1699
Data Index: 8219140 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.8193. Min Act: -0.1700
Data Index: 8059828 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7881. Min Act: -0.1700
Data Index: 1038388 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7881. Min Act: -0.1700
Data Index: 8025189 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7568. Min Act: -0.1700
Data Index: 2705508 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7256. Min Act: -0.1700
Data Index: 8059826 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7256. Min Act: -0.1700
Data Index: 910312 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6943. Min Act: -0.1700
Data Index: 8059831 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4368715 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6631. Min Act: -0.1700
Data Index: 8730956 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6631. Min Act: -0.1700
Data Index: 5266075 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6631. Min Act: -0.1700
Data Index: 2578315 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6631. Min Act: -0.1700
Data Index: 6128230 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19