Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2987. Min Range: -5.2987
Max Act: 5.2987. Min Act: -0.1700
Data Index: 602258 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.8612. Min Act: -0.1700
Data Index: 3613999 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.8925. Min Act: -0.1700
Data Index: 8646136 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.8300. Min Act: -0.1700
Data Index: 6464134 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.7050. Min Act: -0.1700
Data Index: 2603357 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6425. Min Act: -0.1700
Data Index: 7068779 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6425. Min Act: -0.1700
Data Index: 8417957 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6425. Min Act: -0.1700
Data Index: 8417975 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6112. Min Act: -0.1700
Data Index: 236826 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6112. Min Act: -0.1700
Data Index: 1708815 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.6112. Min Act: -0.1700
Data Index: 13035 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5800. Min Act: -0.1700
Data Index: 3338208 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5800. Min Act: -0.1700
Data Index: 783184 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5800. Min Act: -0.1700
Data Index: 5909426 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5487. Min Act: -0.1700
Data Index: 945496 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5487. Min Act: -0.1700
Data Index: 3693082 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5487. Min Act: -0.1700
Data Index: 7646789 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5487. Min Act: -0.1700
Data Index: 3050471 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.5174. Min Act: -0.1700
Data Index: 5362670 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2987. Min Range: -5.2987
Max Act: 4.4862. Min Act: -0.1700
Data Index: 5441734 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19