Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.9827. Min Act: -0.1700
Data Index: 1313913 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.9515. Min Act: -0.1700
Data Index: 4573885 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2453745 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.8890. Min Act: -0.1700
Data Index: 3510179 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.8577. Min Act: -0.1700
Data Index: 4898763 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7952. Min Act: -0.1700
Data Index: 2071830 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7952. Min Act: -0.1700
Data Index: 822130 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7952. Min Act: -0.1700
Data Index: 2365937 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7640. Min Act: -0.1700
Data Index: 3389480 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7327. Min Act: -0.1700
Data Index: 7423854 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7327. Min Act: -0.1700
Data Index: 6227360 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7952. Min Act: -0.1700
Data Index: 1582958 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7327. Min Act: -0.1700
Data Index: 259556 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7015. Min Act: -0.1700
Data Index: 651169 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7327. Min Act: -0.1700
Data Index: 2724387 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7015. Min Act: -0.1700
Data Index: 294143 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7015. Min Act: -0.1700
Data Index: 6136309 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5893982 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.6702. Min Act: -0.1700
Data Index: 5893192 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9827. Min Range: -4.9827
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1587625 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19