Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5961. Min Act: -0.1700
Data Index: 5918671 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5961. Min Act: -0.1700
Data Index: 1007220 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5336. Min Act: -0.1700
Data Index: 7285204 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5961. Min Act: -0.1700
Data Index: 2092960 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5336. Min Act: -0.1700
Data Index: 1653577 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5336. Min Act: -0.1700
Data Index: 284693 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5024. Min Act: -0.1700
Data Index: 942880 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5024. Min Act: -0.1700
Data Index: 6992548 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4711. Min Act: -0.1700
Data Index: 3587017 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4711. Min Act: -0.1700
Data Index: 2279107 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5024. Min Act: -0.1700
Data Index: 3819998 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.5024. Min Act: -0.1700
Data Index: 2964380 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4711. Min Act: -0.1700
Data Index: 3792769 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4086. Min Act: -0.1700
Data Index: 5682842 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4399. Min Act: -0.1700
Data Index: 5016453 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4086. Min Act: -0.1700
Data Index: 5702353 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4399. Min Act: -0.1700
Data Index: 2399638 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4711. Min Act: -0.1700
Data Index: 3372082 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4711. Min Act: -0.1700
Data Index: 3655680 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5961. Min Range: -4.5961
Max Act: 4.4399. Min Act: -0.1700
Data Index: 2626810 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19