Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 690 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.9208. Min Act: -0.1700
Data Index: 43269 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.9208. Min Act: -0.1700
Data Index: 5535498 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.9208. Min Act: -0.1700
Data Index: 601303 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8895. Min Act: -0.1700
Data Index: 4030581 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8895. Min Act: -0.1700
Data Index: 8826722 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8895. Min Act: -0.1700
Data Index: 5130423 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8582. Min Act: -0.1700
Data Index: 6649027 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8582. Min Act: -0.1700
Data Index: 5919019 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.8269. Min Act: -0.1700
Data Index: 1910441 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7957. Min Act: -0.1700
Data Index: 5994829 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7957. Min Act: -0.1700
Data Index: 5810930 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7800. Min Act: -0.1700
Data Index: 1668227 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7957. Min Act: -0.1700
Data Index: 1204112 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7800. Min Act: -0.1700
Data Index: 5641917 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7331. Min Act: -0.1700
Data Index: 6859724 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7488. Min Act: -0.1700
Data Index: 3924983 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7644. Min Act: -0.1700
Data Index: 8025524 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7488. Min Act: -0.1700
Data Index: 7198036 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7175. Min Act: -0.1700
Data Index: 6667468 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9208. Min Range: -3.9208
Max Act: 3.7331. Min Act: -0.1700
Data Index: 5114936 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19