Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1281 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2242. Min Range: -11.2242
Max Act: 11.2242. Min Act: -0.1700
Data Index: 2098627 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2242. Min Range: -11.2242
Max Act: 11.0367. Min Act: -0.1700
Data Index: 7088516 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.8492. Min Act: -0.1700
Data Index: 3594042 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.8492. Min Act: -0.1700
Data Index: 3525253 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.7867. Min Act: -0.1700
Data Index: 2366436 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.7867. Min Act: -0.1700
Data Index: 2032790 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.6617. Min Act: -0.1700
Data Index: 5919532 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.6617. Min Act: -0.1700
Data Index: 3586829 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.6617. Min Act: -0.1700
Data Index: 2440672 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.6617. Min Act: -0.1700
Data Index: 2489966 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.6617. Min Act: -0.1700
Data Index: 185936 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 7915903 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 3002128 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 2811905 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 4060481 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 4668171 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5992. Min Act: -0.1700
Data Index: 4450301 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5367. Min Act: -0.1700
Data Index: 2669686 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.5367. Min Act: -0.1700
Data Index: 7339551 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2242. Min Range: -11.2242
Max Act: 10.4742. Min Act: -0.1700
Data Index: 3886957 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19