Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.5839. Min Act: -0.1700
Data Index: 7192453 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.2714. Min Act: -0.1700
Data Index: 7205395 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.2089. Min Act: -0.1700
Data Index: 6578313 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.2089. Min Act: -0.1700
Data Index: 5134585 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1464. Min Act: -0.1700
Data Index: 4170434 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1776. Min Act: -0.1700
Data Index: 8315618 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1151. Min Act: -0.1700
Data Index: 5833672 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1151. Min Act: -0.1700
Data Index: 7285944 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1151. Min Act: -0.1700
Data Index: 3981678 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0839. Min Act: -0.1700
Data Index: 8705813 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0839. Min Act: -0.1700
Data Index: 4866192 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.1151. Min Act: -0.1700
Data Index: 42369 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0839. Min Act: -0.1700
Data Index: 7293679 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0526. Min Act: -0.1700
Data Index: 2792165 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0526. Min Act: -0.1700
Data Index: 5596150 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5839. Min Range: -6.5839
Max Act: 5.9901. Min Act: -0.1700
Data Index: 3783990 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0214. Min Act: -0.1700
Data Index: 7870976 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0214. Min Act: -0.1700
Data Index: 8536005 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0214. Min Act: -0.1700
Data Index: 1033517 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5839. Min Range: -6.5839
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2027289 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19