Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.2253. Min Act: -0.1700
Data Index: 4739321 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1628. Min Act: -0.1700
Data Index: 2457252 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1940. Min Act: -0.1700
Data Index: 789496 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1628. Min Act: -0.1700
Data Index: 1921325 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1315. Min Act: -0.1700
Data Index: 4252044 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1628. Min Act: -0.1700
Data Index: 377117 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1315. Min Act: -0.1700
Data Index: 5890060 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1315. Min Act: -0.1700
Data Index: 7268939 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.1003. Min Act: -0.1700
Data Index: 4775344 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0690. Min Act: -0.1700
Data Index: 2087005 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0378. Min Act: -0.1700
Data Index: 3071456 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0378. Min Act: -0.1700
Data Index: 7345483 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0378. Min Act: -0.1700
Data Index: 5253060 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2253. Min Range: -5.2253
Max Act: 4.9753. Min Act: -0.1700
Data Index: 6596470 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 5304412 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2242131 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 905742 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2661776 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2563021 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2253. Min Range: -5.2253
Max Act: 5.0065. Min Act: -0.1700
Data Index: 3400075 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19