Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.6593. Min Act: -0.1700
Data Index: 2393723 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.5968. Min Act: -0.1700
Data Index: 1671972 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.5343. Min Act: -0.1700
Data Index: 3183556 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.5343. Min Act: -0.1700
Data Index: 5491475 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.5030. Min Act: -0.1700
Data Index: 1775908 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.4718. Min Act: -0.1700
Data Index: 7624583 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.4718. Min Act: -0.1700
Data Index: 8394117 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.4093. Min Act: -0.1700
Data Index: 4509747 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.4405. Min Act: -0.1700
Data Index: 5018859 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.4093. Min Act: -0.1700
Data Index: 5895172 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3780. Min Act: -0.1700
Data Index: 6725420 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 674704 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 3337562 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5431680 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 8045641 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5575650 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3468. Min Act: -0.1700
Data Index: 2861632 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3780. Min Act: -0.1700
Data Index: 7506945 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3155. Min Act: -0.1700
Data Index: 4532480 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6593. Min Range: -5.6593
Max Act: 5.3155. Min Act: -0.1700
Data Index: 2821096 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19