Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4630 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.5391. Min Act: -0.1700
Data Index: 7784606 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.3353. Min Act: -0.1700
Data Index: 620560 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.3196. Min Act: -0.1700
Data Index: 6575608 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.3039. Min Act: -0.1700
Data Index: 4726880 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2882. Min Act: -0.1700
Data Index: 3817384 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2657310 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2725. Min Act: -0.1700
Data Index: 2978225 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2725. Min Act: -0.1700
Data Index: 5192069 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2411. Min Act: -0.1700
Data Index: 4662933 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2254. Min Act: -0.1700
Data Index: 5069108 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2411. Min Act: -0.1700
Data Index: 400957 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.2097. Min Act: -0.1700
Data Index: 2260300 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1939. Min Act: -0.1700
Data Index: 7014576 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1782. Min Act: -0.1700
Data Index: 6621812 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1782. Min Act: -0.1700
Data Index: 8035274 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1782. Min Act: -0.1700
Data Index: 6329329 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1625. Min Act: -0.1700
Data Index: 3355142 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1625. Min Act: -0.1700
Data Index: 522860 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1782. Min Act: -0.1700
Data Index: 212463 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5391. Min Range: -3.5391
Max Act: 3.1625. Min Act: -0.1700
Data Index: 4788936 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19