Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.4901. Min Act: -0.1700
Data Index: 6381053 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.4589. Min Act: -0.1700
Data Index: 4007420 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.3026. Min Act: -0.1700
Data Index: 463287 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.2714. Min Act: -0.1700
Data Index: 7465032 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.2089. Min Act: -0.1700
Data Index: 6397983 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.1776. Min Act: -0.1700
Data Index: 2394616 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.1776. Min Act: -0.1700
Data Index: 3636279 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.1776. Min Act: -0.1700
Data Index: 4346646 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.1464. Min Act: -0.1700
Data Index: 276383 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.1151. Min Act: -0.1700
Data Index: 8779680 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0839. Min Act: -0.1700
Data Index: 4222718 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0839. Min Act: -0.1700
Data Index: 2576670 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0526. Min Act: -0.1700
Data Index: 8741921 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0526. Min Act: -0.1700
Data Index: 393951 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0526. Min Act: -0.1700
Data Index: 7061587 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0526. Min Act: -0.1700
Data Index: 8181333 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2614129 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4901. Min Range: -6.4901
Max Act: 6.0214. Min Act: -0.1700
Data Index: 7015762 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4901. Min Range: -6.4901
Max Act: 5.9589. Min Act: -0.1700
Data Index: 4286110 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4901. Min Range: -6.4901
Max Act: 5.9901. Min Act: -0.1700
Data Index: 6253308 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19