Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.7296. Min Act: -0.1700
Data Index: 6155590 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.6671. Min Act: -0.1700
Data Index: 5041345 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.4171. Min Act: -0.1700
Data Index: 5283374 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.4171. Min Act: -0.1700
Data Index: 7683525 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.3546. Min Act: -0.1700
Data Index: 4570349 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.3546. Min Act: -0.1700
Data Index: 7374286 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.3546. Min Act: -0.1700
Data Index: 462845 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.2921. Min Act: -0.1700
Data Index: 7374285 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.2296. Min Act: -0.1700
Data Index: 5704919 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.2296. Min Act: -0.1700
Data Index: 5955386 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.2296. Min Act: -0.1700
Data Index: 6573572 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.1671. Min Act: -0.1700
Data Index: 6607996 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.1671. Min Act: -0.1700
Data Index: 8796717 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.0421. Min Act: -0.1700
Data Index: 4668960 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7296. Min Range: -8.7296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 4521519 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.0421. Min Act: -0.1700
Data Index: 1707883 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7296. Min Range: -8.7296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 900346 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.0421. Min Act: -0.1700
Data Index: 5174766 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7296. Min Range: -8.7296
Max Act: 8.0421. Min Act: -0.1700
Data Index: 2335321 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7296. Min Range: -8.7296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 4673725 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19