Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5430 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3975. Min Range: -8.3975
Max Act: 8.3975. Min Act: -0.1700
Data Index: 4566889 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3975. Min Range: -8.3975
Max Act: 8.0850. Min Act: -0.1700
Data Index: 1959178 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.7725. Min Act: -0.1700
Data Index: 811738 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.6787. Min Act: -0.1700
Data Index: 628572 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.5850. Min Act: -0.1700
Data Index: 5801599 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.4287. Min Act: -0.1700
Data Index: 2527406 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.2725. Min Act: -0.1700
Data Index: 8361509 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1787. Min Act: -0.1700
Data Index: 4953950 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1787. Min Act: -0.1700
Data Index: 4424539 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1787. Min Act: -0.1700
Data Index: 3987634 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1787. Min Act: -0.1700
Data Index: 8505964 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1787. Min Act: -0.1700
Data Index: 3426438 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.1475. Min Act: -0.1700
Data Index: 1325860 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0850. Min Act: -0.1700
Data Index: 1792498 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0537. Min Act: -0.1700
Data Index: 7651731 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0537. Min Act: -0.1700
Data Index: 1166744 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0537. Min Act: -0.1700
Data Index: 8093767 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0537. Min Act: -0.1700
Data Index: 2367768 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0537. Min Act: -0.1700
Data Index: 3987633 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3975. Min Range: -8.3975
Max Act: 7.0850. Min Act: -0.1700
Data Index: 590175 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19