Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3159. Min Range: -9.3159
Max Act: 9.3159. Min Act: -0.1700
Data Index: 3983216 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3159. Min Range: -9.3159
Max Act: 9.1284. Min Act: -0.1700
Data Index: 6612833 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6909. Min Act: -0.1700
Data Index: 8120888 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6909. Min Act: -0.1700
Data Index: 8208807 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6909. Min Act: -0.1700
Data Index: 3510428 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6909. Min Act: -0.1700
Data Index: 3057381 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6909. Min Act: -0.1700
Data Index: 4591674 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6284. Min Act: -0.1700
Data Index: 5135783 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.6284. Min Act: -0.1700
Data Index: 4249108 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.5659. Min Act: -0.1700
Data Index: 5706953 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.5659. Min Act: -0.1700
Data Index: 7647884 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.5034. Min Act: -0.1700
Data Index: 2140312 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.5034. Min Act: -0.1700
Data Index: 352106 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.4409. Min Act: -0.1700
Data Index: 7042202 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.4409. Min Act: -0.1700
Data Index: 6484777 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.5034. Min Act: -0.1700
Data Index: 1333346 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.3784. Min Act: -0.1700
Data Index: 232535 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.3784. Min Act: -0.1700
Data Index: 3651239 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.3784. Min Act: -0.1700
Data Index: 2137262 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3159. Min Range: -9.3159
Max Act: 8.3784. Min Act: -0.1700
Data Index: 210806 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19