Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.7156. Min Act: -0.1700
Data Index: 4215864 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.5906. Min Act: -0.1700
Data Index: 3981236 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.5281. Min Act: -0.1700
Data Index: 4322966 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4656. Min Act: -0.1700
Data Index: 5584367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4656. Min Act: -0.1700
Data Index: 5855398 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4656. Min Act: -0.1700
Data Index: 2531481 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1773919 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1875994 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2162129 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4344. Min Act: -0.1700
Data Index: 4739211 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2492588 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 4274725 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 3363201 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 7429837 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 5159624 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.3719. Min Act: -0.1700
Data Index: 2129977 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.3719. Min Act: -0.1700
Data Index: 5690679 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.4031. Min Act: -0.1700
Data Index: 2620135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.3406. Min Act: -0.1700
Data Index: 4681439 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7156. Min Range: -4.7156
Max Act: 4.3406. Min Act: -0.1700
Data Index: 1544553 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19