Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1464 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.6139. Min Act: -0.1700
Data Index: 8732430 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5978. Min Act: -0.1700
Data Index: 5780115 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5656. Min Act: -0.1700
Data Index: 302821 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5656. Min Act: -0.1700
Data Index: 568049 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5495. Min Act: -0.1700
Data Index: 2916296 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5495. Min Act: -0.1700
Data Index: 5668588 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5333. Min Act: -0.1700
Data Index: 1933759 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5333. Min Act: -0.1700
Data Index: 121761 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5333. Min Act: -0.1700
Data Index: 969382 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5333. Min Act: -0.1700
Data Index: 1175672 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5333. Min Act: -0.1700
Data Index: 8723936 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 4198347 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 8436274 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5009. Min Act: -0.1700
Data Index: 7377985 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 6627543 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 2923713 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 8548595 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5009. Min Act: -0.1700
Data Index: 5789380 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.5171. Min Act: -0.1700
Data Index: 30688 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6139. Min Range: -2.6139
Max Act: 2.4847. Min Act: -0.1700
Data Index: 8175375 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19