Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5012 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.8448. Min Act: -0.1700
Data Index: 5374668 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.7823. Min Act: -0.1700
Data Index: 6352762 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.6260. Min Act: -0.1700
Data Index: 7858298 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6540136 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5323. Min Act: -0.1700
Data Index: 3996930 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5010. Min Act: -0.1700
Data Index: 6075380 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.5010. Min Act: -0.1700
Data Index: 3832779 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4698. Min Act: -0.1700
Data Index: 5876730 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4385. Min Act: -0.1700
Data Index: 7488649 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4385. Min Act: -0.1700
Data Index: 3067895 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4073. Min Act: -0.1700
Data Index: 1910390 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3760. Min Act: -0.1700
Data Index: 2117106 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4073. Min Act: -0.1700
Data Index: 1525012 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.4073. Min Act: -0.1700
Data Index: 2236742 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3760. Min Act: -0.1700
Data Index: 741518 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3760. Min Act: -0.1700
Data Index: 5277412 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3760. Min Act: -0.1700
Data Index: 423509 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3448. Min Act: -0.1700
Data Index: 7515154 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4879053 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8448. Min Range: -5.8448
Max Act: 5.3448. Min Act: -0.1700
Data Index: 5572221 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19