Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.7552. Min Act: -0.1700
Data Index: 189088 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.7240. Min Act: -0.1700
Data Index: 5702919 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6927. Min Act: -0.1700
Data Index: 1534674 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6615. Min Act: -0.1700
Data Index: 850079 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6615. Min Act: -0.1700
Data Index: 8250 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5990. Min Act: -0.1700
Data Index: 4186956 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6302. Min Act: -0.1700
Data Index: 4299764 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6302. Min Act: -0.1700
Data Index: 843297 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6302. Min Act: -0.1700
Data Index: 5846096 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5990. Min Act: -0.1700
Data Index: 1195136 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.6302. Min Act: -0.1700
Data Index: 2848361 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5990. Min Act: -0.1700
Data Index: 4691960 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5677. Min Act: -0.1700
Data Index: 5392084 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5677. Min Act: -0.1700
Data Index: 1790178 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5677. Min Act: -0.1700
Data Index: 8077769 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5365. Min Act: -0.1700
Data Index: 5703883 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5365. Min Act: -0.1700
Data Index: 2596031 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5365. Min Act: -0.1700
Data Index: 5966423 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5365. Min Act: -0.1700
Data Index: 1594761 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7552. Min Range: -4.7552
Max Act: 4.5365. Min Act: -0.1700
Data Index: 6985441 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19