Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2291 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1630. Min Range: -3.1630
Max Act: 3.1630. Min Act: -0.1700
Data Index: 5616995 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1630. Min Range: -3.1630
Max Act: 3.1000. Min Act: -0.1700
Data Index: 8629905 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1630. Min Range: -3.1630
Max Act: 3.0053. Min Act: -0.1700
Data Index: 1563502 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1630. Min Range: -3.1630
Max Act: 3.0053. Min Act: -0.1700
Data Index: 2424270 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.9737. Min Act: -0.1700
Data Index: 8197891 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.9103. Min Act: -0.1700
Data Index: 2702837 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.9103. Min Act: -0.1700
Data Index: 1979186 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8786. Min Act: -0.1700
Data Index: 7199167 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8627. Min Act: -0.1700
Data Index: 6798386 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8786. Min Act: -0.1700
Data Index: 6873380 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8627. Min Act: -0.1700
Data Index: 8451226 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8627. Min Act: -0.1700
Data Index: 565938 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8468. Min Act: -0.1700
Data Index: 989484 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8309. Min Act: -0.1700
Data Index: 6658953 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8309. Min Act: -0.1700
Data Index: 4819262 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8309. Min Act: -0.1700
Data Index: 7587200 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8150. Min Act: -0.1700
Data Index: 7669373 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8309. Min Act: -0.1700
Data Index: 5721174 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8309. Min Act: -0.1700
Data Index: 7420823 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1630. Min Range: -3.1630
Max Act: 2.8150. Min Act: -0.1700
Data Index: 1811718 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19