Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9673. Min Act: -0.1700
Data Index: 7277311 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9503. Min Act: -0.1700
Data Index: 3926734 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9334. Min Act: -0.1699
Data Index: 3235272 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9163. Min Act: -0.1700
Data Index: 7943590 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9163. Min Act: -0.1700
Data Index: 8007473 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9163. Min Act: -0.1700
Data Index: 6103981 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9163. Min Act: -0.1700
Data Index: 7494059 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8993. Min Act: -0.1700
Data Index: 8117442 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8822. Min Act: -0.1700
Data Index: 5164391 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8993. Min Act: -0.1700
Data Index: 7535803 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8993. Min Act: -0.1700
Data Index: 3235270 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8822. Min Act: -0.1700
Data Index: 1112362 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8822. Min Act: -0.1700
Data Index: 5500179 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8993. Min Act: -0.1699
Data Index: 7296329 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8822. Min Act: -0.1699
Data Index: 5154560 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8651. Min Act: -0.1700
Data Index: 5029133 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8651. Min Act: -0.1700
Data Index: 4944878 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8651. Min Act: -0.1700
Data Index: 6663240 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8651. Min Act: -0.1700
Data Index: 8477084 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.8651. Min Act: -0.1700
Data Index: 7498909 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19