Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0178. Min Range: -9.0178
Max Act: 9.0178. Min Act: -0.1700
Data Index: 5980161 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.6428. Min Act: -0.1700
Data Index: 2422501 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.7053. Min Act: -0.1700
Data Index: 5765881 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.6428. Min Act: -0.1700
Data Index: 173550 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.5803. Min Act: -0.1700
Data Index: 2524381 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.5803. Min Act: -0.1700
Data Index: 6996788 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.5178. Min Act: -0.1700
Data Index: 4921564 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.5178. Min Act: -0.1700
Data Index: 4222649 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.4553. Min Act: -0.1700
Data Index: 5986050 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.5178. Min Act: -0.1700
Data Index: 6958152 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.4553. Min Act: -0.1700
Data Index: 1206063 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3928. Min Act: -0.1700
Data Index: 4136099 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.4553. Min Act: -0.1700
Data Index: 371126 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3928. Min Act: -0.1700
Data Index: 8041078 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3928. Min Act: -0.1700
Data Index: 3206639 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3928. Min Act: -0.1700
Data Index: 5193985 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3928. Min Act: -0.1700
Data Index: 1829107 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3303. Min Act: -0.1700
Data Index: 5949755 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.2678. Min Act: -0.1700
Data Index: 2297385 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0178. Min Range: -9.0178
Max Act: 8.3303. Min Act: -0.1700
Data Index: 6656730 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19