Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4527 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0079. Min Range: -2.0079
Max Act: 2.0079. Min Act: -0.1700
Data Index: 4991979 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9741. Min Act: -0.1700
Data Index: 1764593 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9741. Min Act: -0.1700
Data Index: 4151561 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9656. Min Act: -0.1700
Data Index: 8799510 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9741. Min Act: -0.1700
Data Index: 4058569 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9741. Min Act: -0.1700
Data Index: 7515251 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9656. Min Act: -0.1700
Data Index: 4649162 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9656. Min Act: -0.1700
Data Index: 2125555 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9656. Min Act: -0.1700
Data Index: 421424 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9571. Min Act: -0.1700
Data Index: 8217911 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9571. Min Act: -0.1700
Data Index: 6243255 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9486. Min Act: -0.1700
Data Index: 3803942 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9316. Min Act: -0.1700
Data Index: 4265096 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9231. Min Act: -0.1700
Data Index: 2423897 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9316. Min Act: -0.1700
Data Index: 3031755 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9401. Min Act: -0.1700
Data Index: 5199082 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9316. Min Act: -0.1700
Data Index: 5683273 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9401. Min Act: -0.1700
Data Index: 3058190 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9231. Min Act: -0.1700
Data Index: 747927 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0079. Min Range: -2.0079
Max Act: 1.9316. Min Act: -0.1700
Data Index: 8000741 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19