Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5436. Min Act: -0.1700
Data Index: 2577449 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5123. Min Act: -0.1700
Data Index: 1623915 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.5123. Min Act: -0.1700
Data Index: 7646465 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4810. Min Act: -0.1700
Data Index: 3303726 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4810. Min Act: -0.1700
Data Index: 677590 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4810. Min Act: -0.1700
Data Index: 8514921 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4496. Min Act: -0.1700
Data Index: 2125109 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4496. Min Act: -0.1700
Data Index: 8621479 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 6372395 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 2552174 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 4846924 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 4748962 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 4666053 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 430651 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3869. Min Act: -0.1700
Data Index: 7015779 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 6827503 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.4183. Min Act: -0.1700
Data Index: 6129378 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3869. Min Act: -0.1700
Data Index: 5312028 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3869. Min Act: -0.1700
Data Index: 1096885 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5436. Min Range: -3.5436
Max Act: 3.3556. Min Act: -0.1700
Data Index: 222609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19