Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 6686010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.4931. Min Act: -0.1700
Data Index: 6561355 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.3993. Min Act: -0.1700
Data Index: 3494226 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.2118. Min Act: -0.1700
Data Index: 8397488 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.1493. Min Act: -0.1700
Data Index: 3742059 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.0868. Min Act: -0.1700
Data Index: 2469027 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.0868. Min Act: -0.1700
Data Index: 4930295 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7118. Min Range: -5.7118
Max Act: 5.0556. Min Act: -0.1700
Data Index: 7354601 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9931. Min Act: -0.1700
Data Index: 7643258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9618. Min Act: -0.1700
Data Index: 6192764 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9306. Min Act: -0.1700
Data Index: 956973 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9306. Min Act: -0.1700
Data Index: 3731352 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9306. Min Act: -0.1700
Data Index: 725165 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9306. Min Act: -0.1700
Data Index: 2223368 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.9306. Min Act: -0.1700
Data Index: 411264 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.8993. Min Act: -0.1700
Data Index: 5461336 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.8993. Min Act: -0.1700
Data Index: 4460185 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.8681. Min Act: -0.1700
Data Index: 3482637 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.8368. Min Act: -0.1700
Data Index: 4852537 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7118. Min Range: -5.7118
Max Act: 4.8368. Min Act: -0.1700
Data Index: 419008 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19