Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6097. Min Range: -8.6097
Max Act: 8.6097. Min Act: -0.1700
Data Index: 980612 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6097. Min Range: -8.6097
Max Act: 8.1097. Min Act: -0.1700
Data Index: 4290645 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.8597. Min Act: -0.1700
Data Index: 1984107 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.8597. Min Act: -0.1700
Data Index: 6991583 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.7972. Min Act: -0.1700
Data Index: 2576425 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.7347. Min Act: -0.1700
Data Index: 6162818 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.7347. Min Act: -0.1700
Data Index: 4564921 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.7347. Min Act: -0.1700
Data Index: 4221605 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.7347. Min Act: -0.1700
Data Index: 1532969 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6722. Min Act: -0.1700
Data Index: 744256 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6722. Min Act: -0.1700
Data Index: 363658 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6722. Min Act: -0.1700
Data Index: 327100 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6722. Min Act: -0.1700
Data Index: 6317359 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6722. Min Act: -0.1700
Data Index: 4564922 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6097. Min Act: -0.1700
Data Index: 1897772 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6097. Min Act: -0.1700
Data Index: 8128358 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.6097. Min Act: -0.1700
Data Index: 3608643 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.4847. Min Act: -0.1700
Data Index: 1864306 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.5472. Min Act: -0.1700
Data Index: 929259 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6097. Min Range: -8.6097
Max Act: 7.5472. Min Act: -0.1700
Data Index: 3020251 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19