Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.8443. Min Act: -0.1700
Data Index: 4097415 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.5943. Min Act: -0.1700
Data Index: 4097414 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.2818. Min Act: -0.1700
Data Index: 3522422 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.2818. Min Act: -0.1700
Data Index: 1145579 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.2193. Min Act: -0.1700
Data Index: 3275871 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.1568. Min Act: -0.1700
Data Index: 1492053 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.1568. Min Act: -0.1700
Data Index: 8816458 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.1568. Min Act: -0.1700
Data Index: 2966916 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.1568. Min Act: -0.1700
Data Index: 3924576 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0943. Min Act: -0.1700
Data Index: 7651855 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0943. Min Act: -0.1700
Data Index: 2308635 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0943. Min Act: -0.1700
Data Index: 7505312 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0943. Min Act: -0.1700
Data Index: 2912959 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0943. Min Act: -0.1700
Data Index: 8422673 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0318. Min Act: -0.1700
Data Index: 6011880 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8443. Min Range: -9.8443
Max Act: 9.0318. Min Act: -0.1700
Data Index: 5730500 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8443. Min Range: -9.8443
Max Act: 8.9693. Min Act: -0.1700
Data Index: 771357 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8443. Min Range: -9.8443
Max Act: 8.9693. Min Act: -0.1700
Data Index: 781408 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8443. Min Range: -9.8443
Max Act: 8.9693. Min Act: -0.1700
Data Index: 5264709 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8443. Min Range: -9.8443
Max Act: 8.9693. Min Act: -0.1700
Data Index: 1492054 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19