Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.6533. Min Act: -0.1700
Data Index: 180195 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.1845. Min Act: -0.1700
Data Index: 1833549 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.0908. Min Act: -0.1700
Data Index: 1803374 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.0908. Min Act: -0.1700
Data Index: 482241 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.0908. Min Act: -0.1700
Data Index: 7360513 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.1220. Min Act: -0.1700
Data Index: 21553 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6533. Min Range: -7.6533
Max Act: 7.0283. Min Act: -0.1700
Data Index: 1626415 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.9658. Min Act: -0.1700
Data Index: 6220062 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.9033. Min Act: -0.1700
Data Index: 1726218 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 1712392 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 202716 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.9033. Min Act: -0.1700
Data Index: 3777031 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8408. Min Act: -0.1700
Data Index: 7359392 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 7888638 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 4083483 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 4488069 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.7470. Min Act: -0.1700
Data Index: 2975365 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.7783. Min Act: -0.1700
Data Index: 7957913 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.7783. Min Act: -0.1700
Data Index: 7399077 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6533. Min Range: -7.6533
Max Act: 6.7783. Min Act: -0.1700
Data Index: 3886545 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19