Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0515. Min Range: -5.0515
Max Act: 5.0515. Min Act: -0.1700
Data Index: 6810466 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.9890. Min Act: -0.1700
Data Index: 7187791 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.9577. Min Act: -0.1700
Data Index: 2361428 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8952. Min Act: -0.1700
Data Index: 2071759 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8952. Min Act: -0.1700
Data Index: 7937003 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8640. Min Act: -0.1700
Data Index: 5128681 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5377629 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 4416331 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 2750400 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 3038397 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8015. Min Act: -0.1700
Data Index: 135608 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8015. Min Act: -0.1700
Data Index: 3038395 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 3382211 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8015. Min Act: -0.1700
Data Index: 7685763 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8022157 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7390. Min Act: -0.1700
Data Index: 12470 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4633408 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8015. Min Act: -0.1700
Data Index: 8178089 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7702. Min Act: -0.1700
Data Index: 2270857 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4083477 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19