Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.1854. Min Act: -0.1700
Data Index: 7246255 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.1229. Min Act: -0.1700
Data Index: 8560671 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0916. Min Act: -0.1700
Data Index: 315424 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0916. Min Act: -0.1700
Data Index: 3702784 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0916. Min Act: -0.1700
Data Index: 276965 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0604. Min Act: -0.1700
Data Index: 7249827 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0604. Min Act: -0.1700
Data Index: 5687575 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0291. Min Act: -0.1700
Data Index: 6148195 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9979. Min Act: -0.1700
Data Index: 3577171 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9979. Min Act: -0.1700
Data Index: 151122 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9979. Min Act: -0.1700
Data Index: 5318121 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1854. Min Range: -6.1854
Max Act: 6.0291. Min Act: -0.1700
Data Index: 6411562 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9354. Min Act: -0.1700
Data Index: 1762177 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9666. Min Act: -0.1700
Data Index: 3506368 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9666. Min Act: -0.1700
Data Index: 1374004 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9041. Min Act: -0.1700
Data Index: 1093770 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2844350 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5099935 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9354. Min Act: -0.1700
Data Index: 5798158 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1854. Min Range: -6.1854
Max Act: 5.9354. Min Act: -0.1700
Data Index: 5658153 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19