Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0825. Min Range: -7.0825
Max Act: 7.0825. Min Act: -0.1700
Data Index: 4382620 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.9887. Min Act: -0.1700
Data Index: 1483736 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.9262. Min Act: -0.1700
Data Index: 4751271 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.8637. Min Act: -0.1700
Data Index: 1010397 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.8325. Min Act: -0.1700
Data Index: 3909352 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.7387. Min Act: -0.1700
Data Index: 7109344 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.7075. Min Act: -0.1700
Data Index: 1513486 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.6762. Min Act: -0.1700
Data Index: 3032580 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1416550 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.6137. Min Act: -0.1700
Data Index: 8432080 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.6450. Min Act: -0.1700
Data Index: 8422645 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.6450. Min Act: -0.1700
Data Index: 5527350 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5825. Min Act: -0.1700
Data Index: 4207733 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4516034 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4254949 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5200. Min Act: -0.1700
Data Index: 3536604 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5512. Min Act: -0.1700
Data Index: 634140 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4164397 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5200. Min Act: -0.1700
Data Index: 7967737 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0825. Min Range: -7.0825
Max Act: 6.5200. Min Act: -0.1700
Data Index: 966610 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19