Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0771. Min Range: -7.0771
Max Act: 7.0771. Min Act: -0.1700
Data Index: 1862142 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.9521. Min Act: -0.1700
Data Index: 2266912 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.7959. Min Act: -0.1700
Data Index: 7013869 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.7334. Min Act: -0.1700
Data Index: 6116281 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.7334. Min Act: -0.1700
Data Index: 4728877 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.7021. Min Act: -0.1700
Data Index: 2652186 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.6709. Min Act: -0.1700
Data Index: 1122347 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.6084. Min Act: -0.1700
Data Index: 1537750 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.5771. Min Act: -0.1700
Data Index: 4621499 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.6084. Min Act: -0.1700
Data Index: 3718692 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.5459. Min Act: -0.1700
Data Index: 6744224 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.5459. Min Act: -0.1700
Data Index: 7257360 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.5771. Min Act: -0.1700
Data Index: 8499315 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.5146. Min Act: -0.1700
Data Index: 6348756 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.4834. Min Act: -0.1700
Data Index: 953449 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.4521. Min Act: -0.1700
Data Index: 4458223 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.4209. Min Act: -0.1700
Data Index: 597869 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.4209. Min Act: -0.1700
Data Index: 3945714 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.3896. Min Act: -0.1700
Data Index: 8121700 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0771. Min Range: -7.0771
Max Act: 6.4209. Min Act: -0.1700
Data Index: 6226257 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19