Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 741 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7650. Min Range: -7.7650
Max Act: 7.7650. Min Act: -0.1700
Data Index: 2808102 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7650. Min Range: -7.7650
Max Act: 7.1400. Min Act: -0.1700
Data Index: 3428050 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.7650. Min Act: -0.1700
Data Index: 116661 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.9838. Min Act: -0.1700
Data Index: 6936882 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 254679 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.3275. Min Act: -0.1700
Data Index: 8367726 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.6713. Min Act: -0.1700
Data Index: 8184085 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.7963. Min Act: -0.1700
Data Index: 5529085 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.6400. Min Act: -0.1700
Data Index: 3862733 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.4525. Min Act: -0.1700
Data Index: 7886931 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.5775. Min Act: -0.1700
Data Index: 4290613 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.6088. Min Act: -0.1700
Data Index: 6496165 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.2650. Min Act: -0.1700
Data Index: 6817436 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.5150. Min Act: -0.1700
Data Index: 618049 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.5463. Min Act: -0.1700
Data Index: 7024943 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.4525. Min Act: -0.1700
Data Index: 1913610 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.5463. Min Act: -0.1700
Data Index: 533639 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.4838. Min Act: -0.1700
Data Index: 2082005 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.4213. Min Act: -0.1700
Data Index: 7024942 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7650. Min Range: -7.7650
Max Act: 6.4525. Min Act: -0.1700
Data Index: 5888763 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19