Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3302950 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.6185. Min Act: -0.1700
Data Index: 8559931 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.6185. Min Act: -0.1700
Data Index: 3722316 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5560. Min Act: -0.1700
Data Index: 4298851 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5248. Min Act: -0.1700
Data Index: 745097 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5248. Min Act: -0.1700
Data Index: 5654726 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5560. Min Act: -0.1700
Data Index: 1783469 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2675803 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4935. Min Act: -0.1700
Data Index: 6575199 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.5248. Min Act: -0.1700
Data Index: 5299578 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4935. Min Act: -0.1700
Data Index: 903144 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4623. Min Act: -0.1700
Data Index: 5603167 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4310. Min Act: -0.1700
Data Index: 2380730 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2585007 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4623. Min Act: -0.1700
Data Index: 8256110 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4310. Min Act: -0.1700
Data Index: 6222745 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2048370 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4310. Min Act: -0.1700
Data Index: 4298838 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.4310. Min Act: -0.1700
Data Index: 2652465 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6498. Min Range: -5.6498
Max Act: 5.3998. Min Act: -0.1700
Data Index: 6819864 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19