Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.1415. Min Act: -0.1700
Data Index: 5938098 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0790. Min Act: -0.1700
Data Index: 6589803 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0790. Min Act: -0.1700
Data Index: 2209283 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0478. Min Act: -0.1700
Data Index: 7324085 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0165. Min Act: -0.1700
Data Index: 1046669 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0165. Min Act: -0.1700
Data Index: 2959614 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1415. Min Range: -7.1415
Max Act: 7.0165. Min Act: -0.1700
Data Index: 3629161 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.9540. Min Act: -0.1700
Data Index: 6647711 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.9540. Min Act: -0.1700
Data Index: 2354978 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.9853. Min Act: -0.1700
Data Index: 1700506 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.9228. Min Act: -0.1700
Data Index: 563115 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8915. Min Act: -0.1700
Data Index: 3997446 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8290. Min Act: -0.1700
Data Index: 1596924 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8603. Min Act: -0.1700
Data Index: 7813893 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 4509473 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.8290. Min Act: -0.1700
Data Index: 930234 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 3814736 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 4220546 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 7010064 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1415. Min Range: -7.1415
Max Act: 6.7978. Min Act: -0.1700
Data Index: 2056281 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19