Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.8675. Min Act: -0.1700
Data Index: 647058 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.8206. Min Act: -0.1700
Data Index: 6089258 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.6642. Min Act: -0.1700
Data Index: 2483801 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.6016. Min Act: -0.1700
Data Index: 8308657 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5860. Min Act: -0.1700
Data Index: 5508031 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4719961 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5703. Min Act: -0.1700
Data Index: 571333 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5547. Min Act: -0.1700
Data Index: 8562967 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5703. Min Act: -0.1700
Data Index: 253051 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5390. Min Act: -0.1700
Data Index: 742407 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5703. Min Act: -0.1700
Data Index: 5108000 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5390. Min Act: -0.1700
Data Index: 249106 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5390. Min Act: -0.1700
Data Index: 3324358 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5390. Min Act: -0.1700
Data Index: 3005344 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5077. Min Act: -0.1700
Data Index: 349468 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.5234. Min Act: -0.1700
Data Index: 6772987 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.4920. Min Act: -0.1700
Data Index: 7047936 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.4920. Min Act: -0.1700
Data Index: 5246957 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.4920. Min Act: -0.1700
Data Index: 8292179 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8675. Min Range: -3.8675
Max Act: 3.4764. Min Act: -0.1700
Data Index: 1084263 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19