Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.8253. Min Act: -0.1700
Data Index: 4537830 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.7628. Min Act: -0.1700
Data Index: 5492084 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6691. Min Act: -0.1700
Data Index: 6104725 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.7003. Min Act: -0.1700
Data Index: 6465934 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6691. Min Act: -0.1700
Data Index: 6480695 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6066. Min Act: -0.1700
Data Index: 67143 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6066. Min Act: -0.1700
Data Index: 7852339 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6066. Min Act: -0.1700
Data Index: 5534211 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5753. Min Act: -0.1700
Data Index: 5928121 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5441. Min Act: -0.1700
Data Index: 7857609 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5753. Min Act: -0.1700
Data Index: 7514706 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5441. Min Act: -0.1700
Data Index: 5219572 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.6066. Min Act: -0.1700
Data Index: 6025846 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5441. Min Act: -0.1700
Data Index: 6777092 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4215961 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5128. Min Act: -0.1700
Data Index: 2395027 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5441. Min Act: -0.1700
Data Index: 5885522 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.5128. Min Act: -0.1700
Data Index: 8077833 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.4503. Min Act: -0.1700
Data Index: 7315087 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8253. Min Range: -4.8253
Max Act: 4.4815. Min Act: -0.1700
Data Index: 2803887 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19