Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.5794. Min Act: -0.1700
Data Index: 5970643 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.5169. Min Act: -0.1700
Data Index: 897733 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.5482. Min Act: -0.1700
Data Index: 7346859 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.4544. Min Act: -0.1700
Data Index: 8160993 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.4232. Min Act: -0.1700
Data Index: 6519310 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3919. Min Act: -0.1700
Data Index: 3765267 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3294. Min Act: -0.1700
Data Index: 8409745 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3607. Min Act: -0.1700
Data Index: 8194082 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3294. Min Act: -0.1700
Data Index: 4525370 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.3294. Min Act: -0.1700
Data Index: 6601227 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2669. Min Act: -0.1700
Data Index: 5436893 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2669. Min Act: -0.1700
Data Index: 4063740 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2669. Min Act: -0.1700
Data Index: 6554483 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2357. Min Act: -0.1700
Data Index: 3780768 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2357. Min Act: -0.1700
Data Index: 168214 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2357. Min Act: -0.1700
Data Index: 6107598 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2357. Min Act: -0.1700
Data Index: 3869054 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2044. Min Act: -0.1700
Data Index: 6764156 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2357. Min Act: -0.1700
Data Index: 7155175 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5794. Min Range: -7.5794
Max Act: 7.2044. Min Act: -0.1700
Data Index: 3281273 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19