Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4887 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.5995. Min Act: -0.1700
Data Index: 7415436 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.5683. Min Act: -0.1700
Data Index: 221117 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.3808. Min Act: -0.1700
Data Index: 8302659 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.4120. Min Act: -0.1700
Data Index: 6510100 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.3495. Min Act: -0.1700
Data Index: 7493222 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.1933. Min Act: -0.1700
Data Index: 3404985 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.1308. Min Act: -0.1700
Data Index: 6415808 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.0995. Min Act: -0.1700
Data Index: 7830601 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.0995. Min Act: -0.1700
Data Index: 5942113 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.0683. Min Act: -0.1700
Data Index: 8030032 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.0058. Min Act: -0.1700
Data Index: 7883936 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5995. Min Range: -7.5995
Max Act: 7.0058. Min Act: -0.1700
Data Index: 8486604 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9745. Min Act: -0.1700
Data Index: 1919365 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9433. Min Act: -0.1700
Data Index: 2936031 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9745. Min Act: -0.1700
Data Index: 2819239 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9745. Min Act: -0.1700
Data Index: 7489449 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9120. Min Act: -0.1700
Data Index: 8627717 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9433. Min Act: -0.1700
Data Index: 2045625 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9745. Min Act: -0.1700
Data Index: 7887947 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5995. Min Range: -7.5995
Max Act: 6.9120. Min Act: -0.1700
Data Index: 8261463 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19