Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 171 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.7081. Min Act: -0.1700
Data Index: 4839354 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.6143. Min Act: -0.1700
Data Index: 7182095 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.5518. Min Act: -0.1700
Data Index: 3751728 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.5206. Min Act: -0.1700
Data Index: 6819809 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.5206. Min Act: -0.1700
Data Index: 6893226 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 5061209 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 170323 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 3882559 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 7600213 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 7401545 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 3882557 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4893. Min Act: -0.1700
Data Index: 8108021 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 3940802 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 8393802 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 21461 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 8259692 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 240224 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 5678849 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 6488239 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7081. Min Range: -4.7081
Max Act: 4.4268. Min Act: -0.1700
Data Index: 785827 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19