Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.5578. Min Act: -0.1700
Data Index: 6469760 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.5578. Min Act: -0.1700
Data Index: 4258692 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.5578. Min Act: -0.1700
Data Index: 2541518 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.4640. Min Act: -0.1700
Data Index: 344279 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.5265. Min Act: -0.1700
Data Index: 1025710 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.3703. Min Act: -0.1700
Data Index: 2441047 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.3703. Min Act: -0.1700
Data Index: 6209815 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.3390. Min Act: -0.1700
Data Index: 5028562 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.2765. Min Act: -0.1700
Data Index: 7366655 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.2140. Min Act: -0.1700
Data Index: 87455 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.2453. Min Act: -0.1700
Data Index: 2737956 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.1828. Min Act: -0.1700
Data Index: 3785853 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.2140. Min Act: -0.1700
Data Index: 1219445 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.1203. Min Act: -0.1700
Data Index: 7258787 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0890. Min Act: -0.1700
Data Index: 4435283 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.1203. Min Act: -0.1700
Data Index: 2149687 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0890. Min Act: -0.1700
Data Index: 6687231 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0578. Min Act: -0.1700
Data Index: 5727479 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0890. Min Act: -0.1700
Data Index: 3271719 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9953. Min Act: -0.1700
Data Index: 2053579 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19