Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7622. Min Act: -0.1700
Data Index: 1410383 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7782. Min Act: -0.1700
Data Index: 7287167 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7622. Min Act: -0.1700
Data Index: 8692685 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7463. Min Act: -0.1700
Data Index: 6037249 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7303. Min Act: -0.1700
Data Index: 7528372 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7303. Min Act: -0.1700
Data Index: 2564841 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7143. Min Act: -0.1700
Data Index: 7563450 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7143. Min Act: -0.1700
Data Index: 2587506 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7143. Min Act: -0.1700
Data Index: 1702572 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.7143. Min Act: -0.1700
Data Index: 2881403 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 2288875 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 350994 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 8714117 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 5612006 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 677549 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 8097727 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6823. Min Act: -0.1700
Data Index: 102058 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6823. Min Act: -0.1700
Data Index: 6908830 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6983. Min Act: -0.1700
Data Index: 7461568 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7782. Min Range: -2.7782
Max Act: 2.6823. Min Act: -0.1700
Data Index: 4297309 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19