Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.9310. Min Act: -0.1700
Data Index: 2068294 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.8060. Min Act: -0.1700
Data Index: 5567666 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.8060. Min Act: -0.1700
Data Index: 5083274 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.6810. Min Act: -0.1700
Data Index: 6504029 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.6810. Min Act: -0.1700
Data Index: 3141102 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.5560. Min Act: -0.1700
Data Index: 6378389 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.4935. Min Act: -0.1700
Data Index: 5320642 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.3998. Min Act: -0.1700
Data Index: 3400220 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.3685. Min Act: -0.1700
Data Index: 6739281 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.3998. Min Act: -0.1700
Data Index: 7356048 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.3685. Min Act: -0.1700
Data Index: 6075960 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2123. Min Act: -0.1700
Data Index: 2461422 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2748. Min Act: -0.1700
Data Index: 152689 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2748. Min Act: -0.1700
Data Index: 631520 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2123. Min Act: -0.1700
Data Index: 6969136 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2748. Min Act: -0.1700
Data Index: 5124077 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.1810. Min Act: -0.1700
Data Index: 6522199 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2123. Min Act: -0.1700
Data Index: 4057530 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.0873. Min Act: -0.1700
Data Index: 1054784 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9310. Min Range: -8.9310
Max Act: 8.2123. Min Act: -0.1700
Data Index: 3812508 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19