Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 350 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.7874. Min Act: -0.1700
Data Index: 7632104 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.6310. Min Act: -0.1700
Data Index: 7345763 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5684. Min Act: -0.1700
Data Index: 437671 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5997. Min Act: -0.1700
Data Index: 5818341 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.5371. Min Act: -0.1700
Data Index: 5045199 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4745. Min Act: -0.1700
Data Index: 7935021 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4745. Min Act: -0.1700
Data Index: 7629890 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4745. Min Act: -0.1700
Data Index: 693981 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4745. Min Act: -0.1700
Data Index: 5123163 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4118. Min Act: -0.1700
Data Index: 8597604 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4118. Min Act: -0.1700
Data Index: 3383409 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.4118. Min Act: -0.1700
Data Index: 7742856 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 2054791 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 5123162 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 3477445 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 8597588 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 472251 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 7692148 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 7804357 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7874. Min Range: -3.7874
Max Act: 3.3804. Min Act: -0.1700
Data Index: 4105171 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19