Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0855. Min Range: -4.0855
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1774020 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8979. Min Act: -0.1700
Data Index: 5801486 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8354. Min Act: -0.1700
Data Index: 7673998 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8354. Min Act: -0.1700
Data Index: 7733299 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8354. Min Act: -0.1700
Data Index: 4288774 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8354. Min Act: -0.1700
Data Index: 6597956 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8354. Min Act: -0.1700
Data Index: 3085888 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8041. Min Act: -0.1700
Data Index: 5461848 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8041. Min Act: -0.1700
Data Index: 3413392 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.8041. Min Act: -0.1700
Data Index: 8116553 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7729. Min Act: -0.1700
Data Index: 3402166 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7729. Min Act: -0.1700
Data Index: 4683530 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7416. Min Act: -0.1700
Data Index: 810510 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7729. Min Act: -0.1700
Data Index: 316087 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7103. Min Act: -0.1700
Data Index: 1676834 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7103. Min Act: -0.1700
Data Index: 3095640 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7416. Min Act: -0.1700
Data Index: 5294394 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4920480 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7416. Min Act: -0.1700
Data Index: 1336169 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0855. Min Range: -4.0855
Max Act: 3.7103. Min Act: -0.1700
Data Index: 7242839 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19