Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4734 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3647. Min Range: -8.3647
Max Act: 8.3647. Min Act: -0.1700
Data Index: 5008623 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9897. Min Act: -0.1700
Data Index: 5036186 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9897. Min Act: -0.1700
Data Index: 982515 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9272. Min Act: -0.1700
Data Index: 3246877 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9272. Min Act: -0.1700
Data Index: 6342628 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9272. Min Act: -0.1700
Data Index: 4798974 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9272. Min Act: -0.1700
Data Index: 4503365 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.9272. Min Act: -0.1700
Data Index: 7344191 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8647. Min Act: -0.1700
Data Index: 1781657 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8647. Min Act: -0.1700
Data Index: 8782047 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8647. Min Act: -0.1700
Data Index: 3660091 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8647. Min Act: -0.1700
Data Index: 8486601 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8022. Min Act: -0.1700
Data Index: 8159300 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.8022. Min Act: -0.1700
Data Index: 8151208 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.7397. Min Act: -0.1700
Data Index: 8486603 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.7397. Min Act: -0.1700
Data Index: 6107845 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.6772. Min Act: -0.1700
Data Index: 5330169 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.7397. Min Act: -0.1700
Data Index: 2994569 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.6772. Min Act: -0.1700
Data Index: 2980336 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3647. Min Range: -8.3647
Max Act: 7.6772. Min Act: -0.1700
Data Index: 2121992 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19