Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5241 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5992. Min Act: -0.1700
Data Index: 8581578 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5680. Min Act: -0.1700
Data Index: 3839380 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3805. Min Act: -0.1700
Data Index: 8416787 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 4063501 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3492. Min Act: -0.1700
Data Index: 1724818 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3492. Min Act: -0.1700
Data Index: 7531312 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3805. Min Act: -0.1700
Data Index: 1030824 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 1724821 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 3839382 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 2378298 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2867. Min Act: -0.1700
Data Index: 8631886 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3180. Min Act: -0.1700
Data Index: 6453064 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2555. Min Act: -0.1700
Data Index: 8581571 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2555. Min Act: -0.1700
Data Index: 6817633 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2555. Min Act: -0.1700
Data Index: 6251177 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 7353276 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 7093283 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 2294373 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 2376111 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2242. Min Act: -0.1700
Data Index: 8581577 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19