Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3483. Min Range: -7.3483
Max Act: 7.3483. Min Act: -0.1700
Data Index: 1213827 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3483. Min Range: -7.3483
Max Act: 7.2233. Min Act: -0.1700
Data Index: 2560525 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3483. Min Range: -7.3483
Max Act: 7.0983. Min Act: -0.1700
Data Index: 3690971 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3483. Min Range: -7.3483
Max Act: 7.0358. Min Act: -0.1700
Data Index: 6208246 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3483. Min Range: -7.3483
Max Act: 7.0046. Min Act: -0.1700
Data Index: 2353195 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.9733. Min Act: -0.1700
Data Index: 768493 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.9421. Min Act: -0.1700
Data Index: 7218015 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.9421. Min Act: -0.1700
Data Index: 369400 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.9108. Min Act: -0.1700
Data Index: 178543 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8796. Min Act: -0.1700
Data Index: 6743410 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8171. Min Act: -0.1700
Data Index: 8345198 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8483. Min Act: -0.1700
Data Index: 7580166 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8483. Min Act: -0.1700
Data Index: 7255679 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8483. Min Act: -0.1700
Data Index: 7236050 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8171. Min Act: -0.1700
Data Index: 8280962 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8171. Min Act: -0.1700
Data Index: 5274650 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.8171. Min Act: -0.1700
Data Index: 7431617 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.7858. Min Act: -0.1700
Data Index: 4702978 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.7858. Min Act: -0.1700
Data Index: 5032914 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3483. Min Range: -7.3483
Max Act: 6.7858. Min Act: -0.1700
Data Index: 1897380 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19