Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4983 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.9035. Min Act: -0.1700
Data Index: 3529637 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.8410. Min Act: -0.1700
Data Index: 4608369 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.8097. Min Act: -0.1700
Data Index: 90810 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1239271 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.8097. Min Act: -0.1700
Data Index: 2676810 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7785. Min Act: -0.1700
Data Index: 6230226 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7472. Min Act: -0.1700
Data Index: 3404380 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7472. Min Act: -0.1700
Data Index: 6272257 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7160. Min Act: -0.1700
Data Index: 3001545 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7160. Min Act: -0.1700
Data Index: 6409511 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7160. Min Act: -0.1700
Data Index: 5169221 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.7160. Min Act: -0.1700
Data Index: 6983112 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6847. Min Act: -0.1700
Data Index: 6576240 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6847. Min Act: -0.1700
Data Index: 1967607 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6847. Min Act: -0.1700
Data Index: 8017705 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6847. Min Act: -0.1700
Data Index: 4504654 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6535. Min Act: -0.1700
Data Index: 2452374 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6847. Min Act: -0.1700
Data Index: 5670384 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6535. Min Act: -0.1700
Data Index: 3115214 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9035. Min Range: -4.9035
Max Act: 4.6535. Min Act: -0.1700
Data Index: 7177520 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19