Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1133 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.5487. Min Act: -0.1700
Data Index: 234591 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.4862. Min Act: -0.1700
Data Index: 5101418 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.4237. Min Act: -0.1700
Data Index: 3656651 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.4237. Min Act: -0.1700
Data Index: 8004243 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.2362. Min Act: -0.1700
Data Index: 8209853 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.2362. Min Act: -0.1700
Data Index: 844000 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1737. Min Act: -0.1700
Data Index: 1574069 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1112. Min Act: -0.1700
Data Index: 5594266 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1112. Min Act: -0.1700
Data Index: 7732082 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1112. Min Act: -0.1700
Data Index: 2064406 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1112. Min Act: -0.1700
Data Index: 4463201 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.9862. Min Act: -0.1700
Data Index: 7358778 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.1112. Min Act: -0.1700
Data Index: 3196378 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5487. Min Range: -8.5487
Max Act: 8.0487. Min Act: -0.1700
Data Index: 8826896 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.9549. Min Act: -0.1700
Data Index: 5867694 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.9237. Min Act: -0.1700
Data Index: 2792129 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.9237. Min Act: -0.1700
Data Index: 3008097 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.7987. Min Act: -0.1700
Data Index: 237736 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.8299. Min Act: -0.1700
Data Index: 7465436 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5487. Min Range: -8.5487
Max Act: 7.8612. Min Act: -0.1700
Data Index: 6359698 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19