Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.3587. Min Act: -0.1700
Data Index: 2588268 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.2959. Min Act: -0.1700
Data Index: 881900 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.2959. Min Act: -0.1700
Data Index: 847886 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.2802. Min Act: -0.1700
Data Index: 809610 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.2802. Min Act: -0.1700
Data Index: 5605972 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.2488. Min Act: -0.1700
Data Index: 615732 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1702. Min Act: -0.1700
Data Index: 8315844 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1702. Min Act: -0.1700
Data Index: 307381 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1387. Min Act: -0.1700
Data Index: 6709475 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1387. Min Act: -0.1700
Data Index: 3751634 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1072. Min Act: -0.1700
Data Index: 2980222 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1230. Min Act: -0.1700
Data Index: 68201 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1072. Min Act: -0.1700
Data Index: 4315146 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1230. Min Act: -0.1700
Data Index: 6326900 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1072. Min Act: -0.1700
Data Index: 1022418 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.1072. Min Act: -0.1700
Data Index: 6597033 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.0914. Min Act: -0.1700
Data Index: 6682395 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.0757. Min Act: -0.1700
Data Index: 6119967 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.0757. Min Act: -0.1700
Data Index: 4091181 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3587. Min Range: -3.3587
Max Act: 3.0599. Min Act: -0.1700
Data Index: 1425216 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19