Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.4018. Min Act: -0.1700
Data Index: 7902509 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.2768. Min Act: -0.1700
Data Index: 2166533 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.2143. Min Act: -0.1700
Data Index: 2022715 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.2143. Min Act: -0.1700
Data Index: 8206095 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.1518. Min Act: -0.1700
Data Index: 5788056 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.0268. Min Act: -0.1700
Data Index: 4911134 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4018. Min Range: -10.4018
Max Act: 10.0268. Min Act: -0.1700
Data Index: 2865289 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.8393. Min Act: -0.1700
Data Index: 6041140 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.9018. Min Act: -0.1700
Data Index: 33557 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.9018. Min Act: -0.1700
Data Index: 7720019 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.9018. Min Act: -0.1700
Data Index: 556664 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.8393. Min Act: -0.1700
Data Index: 7720018 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.7768. Min Act: -0.1700
Data Index: 1305038 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.7143. Min Act: -0.1700
Data Index: 6850811 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.7143. Min Act: -0.1700
Data Index: 5075432 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.7768. Min Act: -0.1700
Data Index: 5765803 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.6518. Min Act: -0.1700
Data Index: 7153986 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.6518. Min Act: -0.1700
Data Index: 1370379 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.5893. Min Act: -0.1700
Data Index: 702001 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4018. Min Range: -10.4018
Max Act: 9.5893. Min Act: -0.1700
Data Index: 4072748 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19