Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.2380. Min Act: -0.1700
Data Index: 5503251 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.2067. Min Act: -0.1700
Data Index: 210857 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.2067. Min Act: -0.1700
Data Index: 5961299 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.1755. Min Act: -0.1700
Data Index: 8548412 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.1130. Min Act: -0.1700
Data Index: 7870054 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.1442. Min Act: -0.1700
Data Index: 563347 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.1130. Min Act: -0.1700
Data Index: 2006703 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.1130. Min Act: -0.1700
Data Index: 6586847 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0817. Min Act: -0.1700
Data Index: 4367938 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7232328 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 8268396 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 485113 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 7858736 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0505. Min Act: -0.1700
Data Index: 1154282 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0817. Min Act: -0.1700
Data Index: 3624867 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2380. Min Range: -6.2380
Max Act: 5.9880. Min Act: -0.1700
Data Index: 6624044 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0192. Min Act: -0.1700
Data Index: 3796867 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6448967 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2380. Min Range: -6.2380
Max Act: 5.9880. Min Act: -0.1700
Data Index: 8702751 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2380. Min Range: -6.2380
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2998265 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19