Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.4311. Min Act: -0.1700
Data Index: 6136393 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.2123. Min Act: -0.1700
Data Index: 7336509 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.1498. Min Act: -0.1700
Data Index: 4454858 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.1498. Min Act: -0.1700
Data Index: 6345173 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.1186. Min Act: -0.1700
Data Index: 2651767 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.1186. Min Act: -0.1700
Data Index: 1632199 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.0561. Min Act: -0.1700
Data Index: 1882170 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.0561. Min Act: -0.1700
Data Index: 7206254 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.0561. Min Act: -0.1700
Data Index: 3161486 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4311. Min Range: -5.4311
Max Act: 5.0248. Min Act: -0.1700
Data Index: 3386875 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9936. Min Act: -0.1700
Data Index: 2840186 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9936. Min Act: -0.1700
Data Index: 4730335 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 7887890 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 3880666 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 3526358 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4906676 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 881122 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 7285155 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6375039 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4311. Min Range: -5.4311
Max Act: 4.9311. Min Act: -0.1700
Data Index: 4496652 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19