Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.5740. Min Act: -0.1700
Data Index: 79210 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.5740. Min Act: -0.1700
Data Index: 5534860 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.5427. Min Act: -0.1700
Data Index: 3253792 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.4490. Min Act: -0.1700
Data Index: 1455673 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.3865. Min Act: -0.1700
Data Index: 6355226 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.3865. Min Act: -0.1700
Data Index: 7051304 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.3552. Min Act: -0.1700
Data Index: 689681 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2302. Min Act: -0.1700
Data Index: 567857 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2302. Min Act: -0.1700
Data Index: 6345596 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2615. Min Act: -0.1700
Data Index: 1816227 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2302. Min Act: -0.1700
Data Index: 6093823 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2302. Min Act: -0.1700
Data Index: 5948607 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.2302. Min Act: -0.1700
Data Index: 1556635 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1990. Min Act: -0.1700
Data Index: 4002950 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1677. Min Act: -0.1700
Data Index: 8532515 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1677. Min Act: -0.1700
Data Index: 2124502 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1677. Min Act: -0.1700
Data Index: 8441484 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1677. Min Act: -0.1700
Data Index: 3410399 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1365. Min Act: -0.1700
Data Index: 3131366 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5740. Min Range: -5.5740
Max Act: 5.1365. Min Act: -0.1700
Data Index: 5579878 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19