Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4853 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5810379 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5486241 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.5521. Min Act: -0.1700
Data Index: 5999709 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.4896. Min Act: -0.1700
Data Index: 3140323 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.4271. Min Act: -0.1700
Data Index: 5400169 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.4584. Min Act: -0.1700
Data Index: 6345612 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3959. Min Act: -0.1700
Data Index: 3188060 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.4271. Min Act: -0.1700
Data Index: 3127230 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3646. Min Act: -0.1700
Data Index: 5999708 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3646. Min Act: -0.1700
Data Index: 1227449 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3646. Min Act: -0.1700
Data Index: 2615719 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3334. Min Act: -0.1700
Data Index: 1961675 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3334. Min Act: -0.1700
Data Index: 4921855 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3646. Min Act: -0.1700
Data Index: 8815958 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3021. Min Act: -0.1700
Data Index: 7528559 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.3021. Min Act: -0.1700
Data Index: 1097573 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.2709. Min Act: -0.1700
Data Index: 7813615 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.2709. Min Act: -0.1700
Data Index: 5131505 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.2709. Min Act: -0.1700
Data Index: 1369024 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6146. Min Range: -5.6146
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5545076 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19