Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.9404. Min Act: -0.1700
Data Index: 1828381 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.9092. Min Act: -0.1700
Data Index: 6470689 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.6279. Min Act: -0.1700
Data Index: 1232292 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.5029. Min Act: -0.1700
Data Index: 6377218 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.4404. Min Act: -0.1700
Data Index: 1990764 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.4404. Min Act: -0.1700
Data Index: 6331213 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.3467. Min Act: -0.1700
Data Index: 4824541 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.3467. Min Act: -0.1700
Data Index: 8591017 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.3154. Min Act: -0.1700
Data Index: 359530 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.3154. Min Act: -0.1700
Data Index: 269241 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2842. Min Act: -0.1700
Data Index: 4610664 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.3154. Min Act: -0.1700
Data Index: 6636368 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2842. Min Act: -0.1700
Data Index: 3629777 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2529. Min Act: -0.1700
Data Index: 5202244 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2217. Min Act: -0.1700
Data Index: 7509223 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2217. Min Act: -0.1700
Data Index: 6094089 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.1904. Min Act: -0.1700
Data Index: 3073902 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.2217. Min Act: -0.1700
Data Index: 4434554 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.1592. Min Act: -0.1700
Data Index: 3389177 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9404. Min Range: -6.9404
Max Act: 6.1279. Min Act: -0.1700
Data Index: 634999 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19