Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.7847. Min Act: -0.1700
Data Index: 7506427 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.6910. Min Act: -0.1700
Data Index: 2348020 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.5972. Min Act: -0.1700
Data Index: 1811572 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.5972. Min Act: -0.1700
Data Index: 1946156 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.5660. Min Act: -0.1700
Data Index: 3905735 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.5035. Min Act: -0.1700
Data Index: 8340068 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4722. Min Act: -0.1700
Data Index: 1490 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4722. Min Act: -0.1700
Data Index: 109865 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4722. Min Act: -0.1700
Data Index: 5694107 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 3205893 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 3058848 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 8235715 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 2849230 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 4457726 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1699
Data Index: 4447077 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4097. Min Act: -0.1700
Data Index: 6538653 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4097. Min Act: -0.1700
Data Index: 806226 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4097. Min Act: -0.1700
Data Index: 3105749 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7038134 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7847. Min Range: -5.7847
Max Act: 5.4410. Min Act: -0.1700
Data Index: 1357717 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19