Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0925. Min Range: -3.0925
Max Act: 3.0925. Min Act: -0.1700
Data Index: 8760786 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9661. Min Act: -0.1700
Data Index: 3952636 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9661. Min Act: -0.1700
Data Index: 2991267 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9503. Min Act: -0.1700
Data Index: 3742966 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9503. Min Act: -0.1700
Data Index: 202569 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9503. Min Act: -0.1700
Data Index: 2918890 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9503. Min Act: -0.1700
Data Index: 1419082 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9503. Min Act: -0.1700
Data Index: 1548945 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9186. Min Act: -0.1700
Data Index: 3290154 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9186. Min Act: -0.1700
Data Index: 2991276 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9345. Min Act: -0.1700
Data Index: 7509933 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9345. Min Act: -0.1700
Data Index: 6043262 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9186. Min Act: -0.1700
Data Index: 6766242 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9186. Min Act: -0.1700
Data Index: 8332312 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9186. Min Act: -0.1700
Data Index: 7992934 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8869. Min Act: -0.1700
Data Index: 7657079 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8711. Min Act: -0.1700
Data Index: 8241679 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8869. Min Act: -0.1700
Data Index: 1431821 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8869. Min Act: -0.1700
Data Index: 5100667 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8711. Min Act: -0.1700
Data Index: 3631226 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19