Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5971 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.8340. Min Act: -0.1700
Data Index: 236674 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.6465. Min Act: -0.1700
Data Index: 3918984 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.6465. Min Act: -0.1700
Data Index: 1152214 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.6152. Min Act: -0.1700
Data Index: 5379653 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.5527. Min Act: -0.1700
Data Index: 3898673 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.5840. Min Act: -0.1700
Data Index: 1220904 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.5527. Min Act: -0.1700
Data Index: 7952091 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.5215. Min Act: -0.1700
Data Index: 692130 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4902. Min Act: -0.1700
Data Index: 5756180 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4902. Min Act: -0.1700
Data Index: 411490 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4902. Min Act: -0.1700
Data Index: 7728200 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4590. Min Act: -0.1700
Data Index: 6590024 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4277. Min Act: -0.1700
Data Index: 7980 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4590. Min Act: -0.1700
Data Index: 1276269 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4590. Min Act: -0.1700
Data Index: 6670650 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4590. Min Act: -0.1700
Data Index: 2165811 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4590. Min Act: -0.1700
Data Index: 6411888 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4277. Min Act: -0.1700
Data Index: 6520110 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.4277. Min Act: -0.1700
Data Index: 4777352 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8340. Min Range: -4.8340
Max Act: 4.3965. Min Act: -0.1700
Data Index: 7584127 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19