Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 487 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.7435. Min Act: -0.1700
Data Index: 1790219 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.7122. Min Act: -0.1700
Data Index: 2998271 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.6497. Min Act: -0.1700
Data Index: 2490814 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.6185. Min Act: -0.1700
Data Index: 3408750 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.6497. Min Act: -0.1700
Data Index: 3254600 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.6185. Min Act: -0.1700
Data Index: 6714887 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.6185. Min Act: -0.1700
Data Index: 8803376 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 3039218 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5573130 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 7831560 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8201387 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8334054 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5778270 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 257726 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 4837976 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5626840 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5560. Min Act: -0.1700
Data Index: 3509703 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5247. Min Act: -0.1700
Data Index: 4371006 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5560. Min Act: -0.1700
Data Index: 4636542 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7435. Min Range: -4.7435
Max Act: 4.5247. Min Act: -0.1700
Data Index: 5195449 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19