Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.9713. Min Act: -0.1700
Data Index: 5478602 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.9401. Min Act: -0.1700
Data Index: 8204691 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.9401. Min Act: -0.1700
Data Index: 7718959 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.8776. Min Act: -0.1700
Data Index: 7441831 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7838. Min Act: -0.1700
Data Index: 8570952 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7838. Min Act: -0.1700
Data Index: 743770 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7213. Min Act: -0.1700
Data Index: 5468042 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7213. Min Act: -0.1700
Data Index: 1255852 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8391097 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8578211 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.6901. Min Act: -0.1700
Data Index: 4558632 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.6901. Min Act: -0.1700
Data Index: 6292633 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.6588. Min Act: -0.1700
Data Index: 4505593 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.6276. Min Act: -0.1700
Data Index: 5376936 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5651. Min Act: -0.1700
Data Index: 8467626 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5338. Min Act: -0.1700
Data Index: 2695308 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5338. Min Act: -0.1700
Data Index: 6098232 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5338. Min Act: -0.1700
Data Index: 3642161 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5338. Min Act: -0.1700
Data Index: 7081084 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9713. Min Range: -5.9713
Max Act: 5.5338. Min Act: -0.1700
Data Index: 5372563 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19