Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6815967 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2010084 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 4126762 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4776. Min Act: -0.1700
Data Index: 2302572 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 7426359 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1202981 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 2082816 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 947970 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4464. Min Act: -0.1700
Data Index: 443788 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 7426847 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 3565406 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5222216 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.4151. Min Act: -0.1700
Data Index: 1074852 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 4524374 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 4659773 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 3634658 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3526. Min Act: -0.1700
Data Index: 4341778 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5695915 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3526. Min Act: -0.1700
Data Index: 2355354 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5401. Min Range: -5.5401
Max Act: 5.3839. Min Act: -0.1700
Data Index: 2415148 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19