Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.5400. Min Act: -0.1700
Data Index: 2775530 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.3837. Min Act: -0.1700
Data Index: 350349 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.3212. Min Act: -0.1700
Data Index: 908823 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.2587. Min Act: -0.1700
Data Index: 5185978 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.2587. Min Act: -0.1700
Data Index: 8514216 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1962. Min Act: -0.1700
Data Index: 204052 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1962. Min Act: -0.1700
Data Index: 1727326 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1650. Min Act: -0.1700
Data Index: 6375186 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1337. Min Act: -0.1700
Data Index: 5987758 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1025. Min Act: -0.1700
Data Index: 5606277 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1650. Min Act: -0.1700
Data Index: 2272899 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1025. Min Act: -0.1700
Data Index: 4957495 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1337. Min Act: -0.1700
Data Index: 4994902 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1337. Min Act: -0.1700
Data Index: 6459783 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.1025. Min Act: -0.1700
Data Index: 754065 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7658818 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.0712. Min Act: -0.1700
Data Index: 946999 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.0712. Min Act: -0.1700
Data Index: 3193702 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.0712. Min Act: -0.1700
Data Index: 1807646 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5400. Min Range: -4.5400
Max Act: 4.0712. Min Act: -0.1700
Data Index: 4395624 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19