Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4201. Min Range: -10.4201
Max Act: 10.4201. Min Act: -0.1700
Data Index: 2725204 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.9826. Min Act: -0.1700
Data Index: 4938058 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.9826. Min Act: -0.1700
Data Index: 5190817 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.9201. Min Act: -0.1700
Data Index: 6336676 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.9201. Min Act: -0.1700
Data Index: 6917489 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.8576. Min Act: -0.1700
Data Index: 6113992 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7951. Min Act: -0.1700
Data Index: 7327507 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7951. Min Act: -0.1700
Data Index: 7943879 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7951. Min Act: -0.1700
Data Index: 5979395 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7951. Min Act: -0.1700
Data Index: 7196884 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7326. Min Act: -0.1700
Data Index: 1275589 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7326. Min Act: -0.1700
Data Index: 7220020 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7326. Min Act: -0.1700
Data Index: 7713541 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.7326. Min Act: -0.1700
Data Index: 5124264 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6701. Min Act: -0.1700
Data Index: 4357870 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6701. Min Act: -0.1700
Data Index: 2960487 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6701. Min Act: -0.1700
Data Index: 5017563 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6076. Min Act: -0.1700
Data Index: 282505 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6076. Min Act: -0.1700
Data Index: 5970902 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4201. Min Range: -10.4201
Max Act: 9.6076. Min Act: -0.1700
Data Index: 3745306 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19