Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.8476. Min Act: -0.1700
Data Index: 6915948 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.8317. Min Act: -0.1700
Data Index: 2113737 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7999. Min Act: -0.1700
Data Index: 5617838 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7840. Min Act: -0.1700
Data Index: 7762325 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7840. Min Act: -0.1700
Data Index: 8653038 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7999. Min Act: -0.1700
Data Index: 3133401 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7999. Min Act: -0.1700
Data Index: 619636 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7999. Min Act: -0.1700
Data Index: 635365 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7840. Min Act: -0.1700
Data Index: 3887154 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7680. Min Act: -0.1700
Data Index: 7512762 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7840. Min Act: -0.1700
Data Index: 3508301 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7680. Min Act: -0.1700
Data Index: 2098119 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7521. Min Act: -0.1700
Data Index: 1277292 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7361. Min Act: -0.1700
Data Index: 7974724 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7201. Min Act: -0.1700
Data Index: 7744295 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7361. Min Act: -0.1700
Data Index: 2468321 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7201. Min Act: -0.1700
Data Index: 2883352 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7041. Min Act: -0.1700
Data Index: 456942 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.7361. Min Act: -0.1700
Data Index: 7358711 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8476. Min Range: -2.8476
Max Act: 2.6721. Min Act: -0.1700
Data Index: 4382824 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19