Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0386. Min Range: -5.0386
Max Act: 5.0386. Min Act: -0.1700
Data Index: 8107850 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0386. Min Range: -5.0386
Max Act: 5.0386. Min Act: -0.1700
Data Index: 4011755 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 3847049 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 459527 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0386. Min Range: -5.0386
Max Act: 5.0386. Min Act: -0.1700
Data Index: 7216506 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7505287 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 8397126 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9761. Min Act: -0.1700
Data Index: 8510629 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 5579315 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 7142352 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 663975 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 3304111 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 7142351 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 5057200 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9136. Min Act: -0.1700
Data Index: 3306561 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9449. Min Act: -0.1700
Data Index: 6214523 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.9136. Min Act: -0.1700
Data Index: 541758 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7852387 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7142350 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0386. Min Range: -5.0386
Max Act: 4.8824. Min Act: -0.1700
Data Index: 1956548 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19