Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.5224. Min Act: -0.1700
Data Index: 7231200 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.4911. Min Act: -0.1700
Data Index: 5264210 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.4598. Min Act: -0.1700
Data Index: 8216767 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.4441. Min Act: -0.1700
Data Index: 4222791 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.3343. Min Act: -0.1700
Data Index: 2908846 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.3029. Min Act: -0.1700
Data Index: 5985852 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2872. Min Act: -0.1700
Data Index: 7403830 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2872. Min Act: -0.1700
Data Index: 5360554 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2872. Min Act: -0.1700
Data Index: 5840576 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2872. Min Act: -0.1700
Data Index: 6419541 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2558. Min Act: -0.1700
Data Index: 4291988 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2558. Min Act: -0.1700
Data Index: 2978538 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2715. Min Act: -0.1700
Data Index: 3769429 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2558. Min Act: -0.1700
Data Index: 8489265 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2401. Min Act: -0.1700
Data Index: 4246342 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2244. Min Act: -0.1700
Data Index: 780016 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2401. Min Act: -0.1700
Data Index: 4065178 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2401. Min Act: -0.1700
Data Index: 2966119 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2244. Min Act: -0.1700
Data Index: 1696303 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5224. Min Range: -3.5224
Max Act: 3.2087. Min Act: -0.1700
Data Index: 3256124 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19