Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.7703. Min Act: -0.1700
Data Index: 203986 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.6453. Min Act: -0.1700
Data Index: 1021402 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.5515. Min Act: -0.1700
Data Index: 476427 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.4890. Min Act: -0.1700
Data Index: 233676 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.3953. Min Act: -0.1700
Data Index: 3738347 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.3953. Min Act: -0.1700
Data Index: 1143092 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7156257 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.2078. Min Act: -0.1700
Data Index: 1796987 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0828. Min Act: -0.1700
Data Index: 3707777 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0828. Min Act: -0.1700
Data Index: 4752451 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0828. Min Act: -0.1700
Data Index: 4577814 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0828. Min Act: -0.1700
Data Index: 6737178 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2305054 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0203. Min Act: -0.1700
Data Index: 8227625 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7703. Min Range: -6.7703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 985111 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7703. Min Range: -6.7703
Max Act: 6.0515. Min Act: -0.1700
Data Index: 6838103 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7703. Min Range: -6.7703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 4356894 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7703. Min Range: -6.7703
Max Act: 5.9890. Min Act: -0.1700
Data Index: 3716282 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7703. Min Range: -6.7703
Max Act: 5.9265. Min Act: -0.1700
Data Index: 3582759 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7703. Min Range: -6.7703
Max Act: 5.9578. Min Act: -0.1700
Data Index: 1112055 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19