Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.7353. Min Act: -0.1700
Data Index: 3188565 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.6103. Min Act: -0.1700
Data Index: 7733794 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5791. Min Act: -0.1700
Data Index: 7426022 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.6103. Min Act: -0.1700
Data Index: 3719616 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5166. Min Act: -0.1700
Data Index: 1862239 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5478. Min Act: -0.1700
Data Index: 2869316 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5478. Min Act: -0.1700
Data Index: 225692 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5166. Min Act: -0.1700
Data Index: 6960046 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.5478. Min Act: -0.1700
Data Index: 4127449 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 5870810 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 3234133 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4228. Min Act: -0.1700
Data Index: 1997559 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 774764 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 506928 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4228. Min Act: -0.1700
Data Index: 8240632 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 3357698 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4541. Min Act: -0.1700
Data Index: 5333827 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4228. Min Act: -0.1700
Data Index: 1055346 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4228. Min Act: -0.1700
Data Index: 1204003 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7353. Min Range: -4.7353
Max Act: 4.4228. Min Act: -0.1700
Data Index: 7602855 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19