Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2368 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 5293295 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.5467. Min Act: -0.1700
Data Index: 1013659 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4842. Min Act: -0.1700
Data Index: 8732126 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 1253484 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.3592. Min Act: -0.1700
Data Index: 2432572 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.3592. Min Act: -0.1700
Data Index: 7925860 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 1668308 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 7665708 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 3160272 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 4404738 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 534003 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 4900767 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2342. Min Act: -0.1700
Data Index: 3471877 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2342. Min Act: -0.1700
Data Index: 3244192 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 8291130 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2342. Min Act: -0.1700
Data Index: 8281628 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2342. Min Act: -0.1700
Data Index: 7796874 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 1253479 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 4076565 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.1717. Min Act: -0.1700
Data Index: 8822766 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19