Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9681. Min Act: -0.1700
Data Index: 563412 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9369. Min Act: -0.1700
Data Index: 1905867 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9369. Min Act: -0.1700
Data Index: 3178890 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.9369. Min Act: -0.1700
Data Index: 673412 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8431. Min Act: -0.1700
Data Index: 8433187 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8431. Min Act: -0.1700
Data Index: 3043827 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 6093808 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 393755 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 563411 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 6307007 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 7067222 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 417644 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.8118. Min Act: -0.1700
Data Index: 5312502 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7805. Min Act: -0.1700
Data Index: 439132 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7805. Min Act: -0.1700
Data Index: 2385273 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7805. Min Act: -0.1700
Data Index: 1009692 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7805. Min Act: -0.1700
Data Index: 8724907 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7805. Min Act: -0.1700
Data Index: 4855036 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7493. Min Act: -0.1700
Data Index: 528448 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9681. Min Range: -3.9681
Max Act: 3.7493. Min Act: -0.1700
Data Index: 3069367 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19