Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.6835. Min Act: -0.1700
Data Index: 7064648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.6679. Min Act: -0.1700
Data Index: 6103230 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.6210. Min Act: -0.1700
Data Index: 4103625 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5740. Min Act: -0.1700
Data Index: 2221346 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5583. Min Act: -0.1700
Data Index: 3860638 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5427. Min Act: -0.1700
Data Index: 211508 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5270. Min Act: -0.1700
Data Index: 1586341 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5270. Min Act: -0.1700
Data Index: 7005064 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5114. Min Act: -0.1700
Data Index: 5544927 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4957. Min Act: -0.1700
Data Index: 8363647 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5114. Min Act: -0.1700
Data Index: 3307536 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4957. Min Act: -0.1700
Data Index: 447652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4800. Min Act: -0.1700
Data Index: 2993108 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.5114. Min Act: -0.1700
Data Index: 8313007 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4957. Min Act: -0.1700
Data Index: 220811 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4800. Min Act: -0.1700
Data Index: 1764213 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4644. Min Act: -0.1700
Data Index: 4864958 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4644. Min Act: -0.1700
Data Index: 3931177 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4800. Min Act: -0.1700
Data Index: 1959316 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6835. Min Range: -3.6835
Max Act: 3.4644. Min Act: -0.1700
Data Index: 6051745 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19