Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4224 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.5545. Min Act: -0.1700
Data Index: 6590564 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.3982. Min Act: -0.1700
Data Index: 7751598 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.3357. Min Act: -0.1700
Data Index: 7724709 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.3045. Min Act: -0.1700
Data Index: 6519413 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.2420. Min Act: -0.1700
Data Index: 7290222 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.2420. Min Act: -0.1700
Data Index: 6912093 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.2107. Min Act: -0.1700
Data Index: 2117436 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.2107. Min Act: -0.1700
Data Index: 5102492 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1795. Min Act: -0.1700
Data Index: 8765265 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6381737 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1482. Min Act: -0.1700
Data Index: 1313813 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1482. Min Act: -0.1700
Data Index: 7812019 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1170. Min Act: -0.1700
Data Index: 2236109 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0857. Min Act: -0.1700
Data Index: 458844 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.1170. Min Act: -0.1700
Data Index: 8201519 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0857. Min Act: -0.1700
Data Index: 1731910 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6405007 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0857. Min Act: -0.1700
Data Index: 1313811 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8474220 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5545. Min Range: -5.5545
Max Act: 5.0857. Min Act: -0.1700
Data Index: 3504861 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19