Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.8128. Min Act: -0.1700
Data Index: 5982561 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.7503. Min Act: -0.1700
Data Index: 7439167 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.6878. Min Act: -0.1700
Data Index: 3612752 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.5940. Min Act: -0.1700
Data Index: 6848262 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.4690. Min Act: -0.1700
Data Index: 116488 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1440227 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.4065. Min Act: -0.1700
Data Index: 8489310 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.3440. Min Act: -0.1700
Data Index: 2534563 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.3440. Min Act: -0.1700
Data Index: 1996513 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.3128. Min Act: -0.1700
Data Index: 4251342 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.3128. Min Act: -0.1700
Data Index: 7373259 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.2815. Min Act: -0.1700
Data Index: 4773907 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.2190. Min Act: -0.1700
Data Index: 687685 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1878. Min Act: -0.1700
Data Index: 2604351 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1565. Min Act: -0.1700
Data Index: 7665233 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1565. Min Act: -0.1700
Data Index: 1374957 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1878. Min Act: -0.1700
Data Index: 3805806 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 1289797 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1565. Min Act: -0.1700
Data Index: 5619523 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8128. Min Range: -6.8128
Max Act: 6.1253. Min Act: -0.1700
Data Index: 2368184 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19