Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.4810. Min Act: -0.1700
Data Index: 667393 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.2310. Min Act: -0.1700
Data Index: 7166807 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.1685. Min Act: -0.1700
Data Index: 2363738 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.1685. Min Act: -0.1700
Data Index: 2363737 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.1685. Min Act: -0.1700
Data Index: 1612048 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4810. Min Range: -11.4810
Max Act: 11.1060. Min Act: -0.1700
Data Index: 4440269 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.9810. Min Act: -0.1700
Data Index: 2781632 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.9810. Min Act: -0.1700
Data Index: 197836 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.9185. Min Act: -0.1700
Data Index: 7852122 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.9810. Min Act: -0.1700
Data Index: 2337469 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.8560. Min Act: -0.1700
Data Index: 2638432 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.9185. Min Act: -0.1700
Data Index: 5821467 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.8560. Min Act: -0.1700
Data Index: 3428657 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7935. Min Act: -0.1700
Data Index: 5223494 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7935. Min Act: -0.1700
Data Index: 6447907 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7310. Min Act: -0.1700
Data Index: 5698144 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7310. Min Act: -0.1700
Data Index: 990824 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7310. Min Act: -0.1699
Data Index: 6676015 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.7310. Min Act: -0.1700
Data Index: 8157507 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4810. Min Range: -11.4810
Max Act: 10.6685. Min Act: -0.1700
Data Index: 1595260 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19