Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4189 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7978. Min Range: -8.7978
Max Act: 8.7978. Min Act: -0.1700
Data Index: 6416493 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7978. Min Range: -8.7978
Max Act: 8.3603. Min Act: -0.1700
Data Index: 6045922 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7978. Min Range: -8.7978
Max Act: 8.2978. Min Act: -0.1700
Data Index: 8401389 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7978. Min Act: -0.1700
Data Index: 6009710 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7978. Min Act: -0.1700
Data Index: 7541528 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7978. Min Act: -0.1700
Data Index: 7088143 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7041. Min Act: -0.1700
Data Index: 2350910 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4689299 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.6728. Min Act: -0.1700
Data Index: 3697121 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4056274 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.6416. Min Act: -0.1700
Data Index: 5803309 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.6416. Min Act: -0.1700
Data Index: 8048358 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.5791. Min Act: -0.1700
Data Index: 3821377 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.5791. Min Act: -0.1700
Data Index: 8199357 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.5166. Min Act: -0.1700
Data Index: 1373743 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.5166. Min Act: -0.1700
Data Index: 6517692 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.5166. Min Act: -0.1700
Data Index: 7716995 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.4853. Min Act: -0.1700
Data Index: 7235240 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.4853. Min Act: -0.1700
Data Index: 5893966 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7978. Min Range: -8.7978
Max Act: 7.4853. Min Act: -0.1700
Data Index: 4612512 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19