Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.8284. Min Act: -0.1700
Data Index: 8552518 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7972. Min Act: -0.1700
Data Index: 5752446 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7347. Min Act: -0.1700
Data Index: 4698532 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 2992134 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 4660934 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 5761920 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 3393269 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5784. Min Act: -0.1700
Data Index: 2321978 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 5645952 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4222. Min Act: -0.1700
Data Index: 8139412 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4534. Min Act: -0.1700
Data Index: 5671881 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4534. Min Act: -0.1700
Data Index: 6150462 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4187203 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4729476 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4729475 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4698531 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3284. Min Act: -0.1700
Data Index: 6150472 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.3597. Min Act: -0.1700
Data Index: 5055154 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.2659. Min Act: -0.1700
Data Index: 8066947 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.2972. Min Act: -0.1700
Data Index: 6841786 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19