Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.7456. Min Act: -0.1700
Data Index: 3386377 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.6831. Min Act: -0.1700
Data Index: 3353743 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.5268. Min Act: -0.1700
Data Index: 7836821 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.4643. Min Act: -0.1700
Data Index: 7282021 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7485246 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.3706. Min Act: -0.1700
Data Index: 2283396 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.3081. Min Act: -0.1700
Data Index: 4546412 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2768. Min Act: -0.1700
Data Index: 6815113 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2768. Min Act: -0.1700
Data Index: 5389502 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 8350772 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 7338901 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 1708039 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1831. Min Act: -0.1700
Data Index: 5129790 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.2143. Min Act: -0.1700
Data Index: 2178994 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1518. Min Act: -0.1700
Data Index: 7481115 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1373654 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1518. Min Act: -0.1700
Data Index: 621723 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1206. Min Act: -0.1700
Data Index: 4004028 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1206. Min Act: -0.1700
Data Index: 1342560 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7456. Min Range: -6.7456
Max Act: 6.1206. Min Act: -0.1700
Data Index: 4255876 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19