Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6110 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 986837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.0378. Min Act: -0.1700
Data Index: 4564779 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9753. Min Act: -0.1700
Data Index: 1346238 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.9753. Min Act: -0.1700
Data Index: 4323034 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8815. Min Act: -0.1700
Data Index: 6789506 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8503. Min Act: -0.1700
Data Index: 4072965 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.8503. Min Act: -0.1700
Data Index: 321198 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7878. Min Act: -0.1700
Data Index: 7236045 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7878. Min Act: -0.1700
Data Index: 5551336 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7565. Min Act: -0.1700
Data Index: 3875715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7878. Min Act: -0.1700
Data Index: 2593829 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7565. Min Act: -0.1700
Data Index: 2168133 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7565. Min Act: -0.1700
Data Index: 4494498 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7565. Min Act: -0.1700
Data Index: 8142546 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.6940. Min Act: -0.1700
Data Index: 4593247 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.7253. Min Act: -0.1700
Data Index: 3096453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 8196840 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.6940. Min Act: -0.1700
Data Index: 3694734 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 4231115 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4128. Min Range: -5.4128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 2248116 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19