Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.5144. Min Act: -0.1700
Data Index: 7266407 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.4519. Min Act: -0.1700
Data Index: 1131571 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.3894. Min Act: -0.1700
Data Index: 3128528 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.2644. Min Act: -0.1700
Data Index: 5869280 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.2019. Min Act: -0.1700
Data Index: 6783437 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.1706. Min Act: -0.1700
Data Index: 1406170 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.1394. Min Act: -0.1700
Data Index: 4492608 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.0769. Min Act: -0.1700
Data Index: 2872221 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.0769. Min Act: -0.1700
Data Index: 739427 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.0144. Min Act: -0.1700
Data Index: 7855206 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5144. Min Range: -6.5144
Max Act: 6.0144. Min Act: -0.1700
Data Index: 6241548 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2458329 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9831. Min Act: -0.1700
Data Index: 7112113 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5616225 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9519. Min Act: -0.1700
Data Index: 1674451 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9519. Min Act: -0.1700
Data Index: 3262058 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9519. Min Act: -0.1700
Data Index: 2098831 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9206. Min Act: -0.1700
Data Index: 5424004 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9206. Min Act: -0.1700
Data Index: 593259 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5144. Min Range: -6.5144
Max Act: 5.9206. Min Act: -0.1700
Data Index: 7680244 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19