Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.6951. Min Act: -0.1700
Data Index: 7311934 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.6326. Min Act: -0.1700
Data Index: 1481452 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.6014. Min Act: -0.1700
Data Index: 8627609 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.6014. Min Act: -0.1700
Data Index: 6178110 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.5701. Min Act: -0.1700
Data Index: 7405063 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.5389. Min Act: -0.1700
Data Index: 4732553 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.5389. Min Act: -0.1700
Data Index: 5840170 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.5076. Min Act: -0.1700
Data Index: 6579995 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4764. Min Act: -0.1700
Data Index: 1762537 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4764. Min Act: -0.1700
Data Index: 627073 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 4923966 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4764. Min Act: -0.1700
Data Index: 1541437 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4139. Min Act: -0.1700
Data Index: 563058 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 8144184 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 4594003 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 1197381 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 6305563 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 7159070 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4451. Min Act: -0.1700
Data Index: 842099 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6951. Min Range: -4.6951
Max Act: 4.4139. Min Act: -0.1700
Data Index: 3011869 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19