Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1626. Min Range: -7.1626
Max Act: 7.1626. Min Act: -0.1700
Data Index: 5407022 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1626. Min Range: -7.1626
Max Act: 7.1001. Min Act: -0.1700
Data Index: 1156602 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.9439. Min Act: -0.1700
Data Index: 2706989 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.7564. Min Act: -0.1700
Data Index: 2994217 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.7564. Min Act: -0.1700
Data Index: 1947090 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.7251. Min Act: -0.1700
Data Index: 5215935 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.7251. Min Act: -0.1700
Data Index: 4442905 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6939. Min Act: -0.1700
Data Index: 5348899 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6939. Min Act: -0.1700
Data Index: 1371170 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6939. Min Act: -0.1700
Data Index: 8362619 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6626. Min Act: -0.1700
Data Index: 3253349 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6939. Min Act: -0.1700
Data Index: 6936781 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6314. Min Act: -0.1700
Data Index: 1304790 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6314. Min Act: -0.1700
Data Index: 6959067 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6314. Min Act: -0.1700
Data Index: 880336 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.6314. Min Act: -0.1700
Data Index: 3311921 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.5689. Min Act: -0.1700
Data Index: 594758 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.5689. Min Act: -0.1700
Data Index: 3418219 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.5689. Min Act: -0.1700
Data Index: 1062903 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1626. Min Range: -7.1626
Max Act: 6.5689. Min Act: -0.1700
Data Index: 997976 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19