Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5841 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.7420. Min Act: -0.1700
Data Index: 3001827 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.6169. Min Act: -0.1700
Data Index: 6619023 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5230. Min Act: -0.1700
Data Index: 5606867 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.5073. Min Act: -0.1700
Data Index: 6625931 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.4760. Min Act: -0.1700
Data Index: 4755001 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.4760. Min Act: -0.1700
Data Index: 5059076 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.4603. Min Act: -0.1700
Data Index: 8792405 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.4290. Min Act: -0.1700
Data Index: 53407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3976. Min Act: -0.1700
Data Index: 3545128 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3819. Min Act: -0.1700
Data Index: 1617998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3819. Min Act: -0.1700
Data Index: 6776450 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3662. Min Act: -0.1700
Data Index: 2806106 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3976. Min Act: -0.1700
Data Index: 6046224 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3506. Min Act: -0.1700
Data Index: 1341205 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3349. Min Act: -0.1700
Data Index: 7362426 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4413659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4038268 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3349. Min Act: -0.1700
Data Index: 567217 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3192. Min Act: -0.1700
Data Index: 3595358 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7420. Min Range: -3.7420
Max Act: 3.3192. Min Act: -0.1700
Data Index: 7056210 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19