Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.7240. Min Act: -0.1700
Data Index: 8146348 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.7240. Min Act: -0.1700
Data Index: 6229040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.6615. Min Act: -0.1700
Data Index: 846196 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.6615. Min Act: -0.1700
Data Index: 5824466 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.6615. Min Act: -0.1700
Data Index: 2860184 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 2934114 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.6615. Min Act: -0.1700
Data Index: 3507356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.6615. Min Act: -0.1700
Data Index: 3584731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1697
Data Index: 304112 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 7290917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1687
Data Index: 8415315 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 4952739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 4887703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 4876109 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 791067 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 4639353 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1700
Data Index: 6900571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5365. Min Act: -0.1700
Data Index: 431016 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5365. Min Act: -0.1687
Data Index: 2025189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7240. Min Range: -6.7240
Max Act: 6.5990. Min Act: -0.1699
Data Index: 105101 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19