Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.2459. Min Act: -0.1700
Data Index: 6220686 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.2128. Min Act: -0.1700
Data Index: 4643327 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1796. Min Act: -0.1700
Data Index: 6952371 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1629. Min Act: -0.1700
Data Index: 977753 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1796. Min Act: -0.1700
Data Index: 479923 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1463. Min Act: -0.1700
Data Index: 7514107 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 6779115 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1463. Min Act: -0.1700
Data Index: 2327685 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1129. Min Act: -0.1700
Data Index: 4191140 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1129. Min Act: -0.1700
Data Index: 4530100 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1129. Min Act: -0.1700
Data Index: 3036112 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.1129. Min Act: -0.1700
Data Index: 5590210 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 6698472 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 3705053 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 2139456 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 6681161 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0961. Min Act: -0.1700
Data Index: 6561328 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0626. Min Act: -0.1700
Data Index: 2529652 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0626. Min Act: -0.1700
Data Index: 7485707 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2459. Min Range: -2.2459
Max Act: 2.0794. Min Act: -0.1700
Data Index: 4542852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19