Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4118 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.4015. Min Act: -0.1700
Data Index: 7584421 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.3545. Min Act: -0.1700
Data Index: 7983174 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.3388. Min Act: -0.1700
Data Index: 4032239 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.2760. Min Act: -0.1700
Data Index: 4402964 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.2446. Min Act: -0.1700
Data Index: 3252871 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1974. Min Act: -0.1700
Data Index: 4820344 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1660. Min Act: -0.1700
Data Index: 5069440 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1345. Min Act: -0.1700
Data Index: 3742098 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1502. Min Act: -0.1700
Data Index: 8427243 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1660. Min Act: -0.1700
Data Index: 4312718 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1345. Min Act: -0.1700
Data Index: 5966754 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1187. Min Act: -0.1700
Data Index: 8658338 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1187. Min Act: -0.1700
Data Index: 4531967 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1187. Min Act: -0.1700
Data Index: 8758819 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.1030. Min Act: -0.1700
Data Index: 2427894 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.0714. Min Act: -0.1700
Data Index: 1489538 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.0714. Min Act: -0.1700
Data Index: 2981546 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.0714. Min Act: -0.1700
Data Index: 4140554 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.0399. Min Act: -0.1700
Data Index: 970430 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4015. Min Range: -3.4015
Max Act: 3.0241. Min Act: -0.1700
Data Index: 5653839 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19