Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8961. Min Act: -0.1700
Data Index: 7729846 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8643. Min Act: -0.1700
Data Index: 2532231 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8643. Min Act: -0.1700
Data Index: 8714026 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8484. Min Act: -0.1700
Data Index: 2842511 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8484. Min Act: -0.1700
Data Index: 331086 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8484. Min Act: -0.1700
Data Index: 7195819 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8325. Min Act: -0.1700
Data Index: 2121220 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8484. Min Act: -0.1700
Data Index: 1459801 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8166. Min Act: -0.1700
Data Index: 3176822 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8325. Min Act: -0.1700
Data Index: 4931968 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8007. Min Act: -0.1700
Data Index: 4526375 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8007. Min Act: -0.1700
Data Index: 1686445 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7848. Min Act: -0.1700
Data Index: 2286805 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7848. Min Act: -0.1700
Data Index: 3250913 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7688. Min Act: -0.1700
Data Index: 2172631 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.8007. Min Act: -0.1700
Data Index: 6125136 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7848. Min Act: -0.1700
Data Index: 891663 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7529. Min Act: -0.1700
Data Index: 3534244 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7529. Min Act: -0.1700
Data Index: 3154436 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8961. Min Range: -2.8961
Max Act: 2.7529. Min Act: -0.1700
Data Index: 534487 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19