Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.6220. Min Act: -0.1700
Data Index: 5752583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5907. Min Act: -0.1700
Data Index: 2436346 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5594. Min Act: -0.1700
Data Index: 6164388 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5594. Min Act: -0.1700
Data Index: 2474663 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5594. Min Act: -0.1700
Data Index: 4103523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 6837349 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 4479199 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 3731022 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 8485378 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 7107032 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 2132006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.4968. Min Act: -0.1700
Data Index: 1698223 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 5045893 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 6618229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 5238453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.4968. Min Act: -0.1700
Data Index: 5373187 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 1909997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 4027211 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 6568357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6220. Min Range: -3.6220
Max Act: 3.5281. Min Act: -0.1700
Data Index: 5420774 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19