Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.2124. Min Act: -0.1700
Data Index: 7388031 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.2124. Min Act: -0.1700
Data Index: 7772479 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.1811. Min Act: -0.1700
Data Index: 4023232 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.1499. Min Act: -0.1700
Data Index: 5063564 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.1186. Min Act: -0.1700
Data Index: 5992683 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0874. Min Act: -0.1700
Data Index: 2306207 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0561. Min Act: -0.1700
Data Index: 6411308 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 8538877 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9936. Min Act: -0.1700
Data Index: 8681530 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0561. Min Act: -0.1700
Data Index: 1663092 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 7225365 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 6725746 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 5496300 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9624. Min Act: -0.1700
Data Index: 3702431 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2124. Min Range: -6.2124
Max Act: 6.0249. Min Act: -0.1700
Data Index: 6261271 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9936. Min Act: -0.1700
Data Index: 5370433 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9936. Min Act: -0.1700
Data Index: 3489305 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9936. Min Act: -0.1700
Data Index: 3024074 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2401458 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2124. Min Range: -6.2124
Max Act: 5.9624. Min Act: -0.1700
Data Index: 1752488 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19