Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0324. Min Range: -9.0324
Max Act: 9.0324. Min Act: -0.1700
Data Index: 2237350 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.8449. Min Act: -0.1700
Data Index: 8523454 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.6574. Min Act: -0.1700
Data Index: 8713076 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.5324. Min Act: -0.1700
Data Index: 1445371 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.4074. Min Act: -0.1700
Data Index: 3818853 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.4074. Min Act: -0.1700
Data Index: 5851239 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.3449. Min Act: -0.1700
Data Index: 4608216 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.3449. Min Act: -0.1700
Data Index: 1445372 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 5071668 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 7947495 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 5334485 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 2554312 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 7414222 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 7947494 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 3938722 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2199. Min Act: -0.1700
Data Index: 833304 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 2732215 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 5666697 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2824. Min Act: -0.1700
Data Index: 5122470 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0324. Min Range: -9.0324
Max Act: 8.2199. Min Act: -0.1700
Data Index: 5954064 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19