Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.4648. Min Act: -0.1700
Data Index: 3676545 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.3398. Min Act: -0.1700
Data Index: 899066 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.3398. Min Act: -0.1700
Data Index: 3319356 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.3085. Min Act: -0.1700
Data Index: 506229 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.2460. Min Act: -0.1700
Data Index: 4271344 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1835. Min Act: -0.1700
Data Index: 5931982 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.2148. Min Act: -0.1700
Data Index: 3974436 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1523. Min Act: -0.1700
Data Index: 511191 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1523. Min Act: -0.1700
Data Index: 6585136 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1523. Min Act: -0.1700
Data Index: 3676540 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1523. Min Act: -0.1700
Data Index: 658671 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 594566 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 5746801 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 553364 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8686349 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8296573 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.0898. Min Act: -0.1700
Data Index: 8368 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.0898. Min Act: -0.1700
Data Index: 6486528 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 7262209 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.0898. Min Act: -0.1700
Data Index: 3567605 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19