Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3656. Min Range: -4.3656
Max Act: 4.3656. Min Act: -0.1700
Data Index: 4493881 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3656. Min Range: -4.3656
Max Act: 4.0530. Min Act: -0.1700
Data Index: 5594624 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3656. Min Range: -4.3656
Max Act: 4.0530. Min Act: -0.1700
Data Index: 8684760 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3656. Min Range: -4.3656
Max Act: 4.0218. Min Act: -0.1700
Data Index: 784843 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.9280. Min Act: -0.1700
Data Index: 6940137 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.9280. Min Act: -0.1700
Data Index: 8525296 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8654. Min Act: -0.1700
Data Index: 6872124 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8654. Min Act: -0.1700
Data Index: 6497049 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8654. Min Act: -0.1700
Data Index: 4712449 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8654. Min Act: -0.1700
Data Index: 5844462 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1317633 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1177895 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 6227598 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 8489737 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 8144831 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8029. Min Act: -0.1700
Data Index: 4131125 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8029. Min Act: -0.1700
Data Index: 3899372 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8029. Min Act: -0.1700
Data Index: 2907136 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8029. Min Act: -0.1700
Data Index: 5135326 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3656. Min Range: -4.3656
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1163682 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19