Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.7854. Min Act: -0.1700
Data Index: 8525698 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.7542. Min Act: -0.1700
Data Index: 875312 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.7229. Min Act: -0.1700
Data Index: 2090181 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6917. Min Act: -0.1700
Data Index: 5374092 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.7229. Min Act: -0.1700
Data Index: 4940571 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6604. Min Act: -0.1700
Data Index: 2534240 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5688459 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5535822 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6292. Min Act: -0.1700
Data Index: 4626153 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6292. Min Act: -0.1700
Data Index: 5111902 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8241123 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5979. Min Act: -0.1700
Data Index: 2282175 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5979. Min Act: -0.1700
Data Index: 6421037 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5667. Min Act: -0.1700
Data Index: 6231342 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5667. Min Act: -0.1700
Data Index: 2804093 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5979. Min Act: -0.1700
Data Index: 6350021 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5667. Min Act: -0.1700
Data Index: 2511 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5667. Min Act: -0.1700
Data Index: 560423 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5118848 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7854. Min Range: -4.7854
Max Act: 4.5667. Min Act: -0.1700
Data Index: 6579149 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19