Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.2704. Min Act: -0.1700
Data Index: 6012313 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.1454. Min Act: -0.1700
Data Index: 4040080 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.0516. Min Act: -0.1700
Data Index: 273393 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.0829. Min Act: -0.1700
Data Index: 2786450 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2704. Min Range: -5.2704
Max Act: 5.0204. Min Act: -0.1700
Data Index: 4040085 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.9266. Min Act: -0.1700
Data Index: 7788802 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8954. Min Act: -0.1700
Data Index: 2390003 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.9266. Min Act: -0.1700
Data Index: 7040179 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8954. Min Act: -0.1700
Data Index: 922956 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.9266. Min Act: -0.1700
Data Index: 2338625 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8954. Min Act: -0.1700
Data Index: 1880575 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 7464795 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 5730456 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4269115 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8641. Min Act: -0.1700
Data Index: 90131 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 4040089 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 5143589 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8329. Min Act: -0.1700
Data Index: 5320110 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4806288 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2704. Min Range: -5.2704
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4950024 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19