Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.8763. Min Act: -0.1700
Data Index: 473208 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.8138. Min Act: -0.1700
Data Index: 5422060 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.5326. Min Act: -0.1700
Data Index: 679204 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.5013. Min Act: -0.1700
Data Index: 8295166 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.4388. Min Act: -0.1700
Data Index: 8045537 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.4388. Min Act: -0.1700
Data Index: 3316839 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3451. Min Act: -0.1700
Data Index: 5407940 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3763. Min Act: -0.1700
Data Index: 6875095 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3451. Min Act: -0.1700
Data Index: 8390080 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3451. Min Act: -0.1700
Data Index: 2989000 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3138. Min Act: -0.1700
Data Index: 5201090 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.3451. Min Act: -0.1700
Data Index: 6917348 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2826. Min Act: -0.1700
Data Index: 3486154 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2513. Min Act: -0.1700
Data Index: 3016376 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2513. Min Act: -0.1700
Data Index: 4454725 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2513. Min Act: -0.1700
Data Index: 327258 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2513. Min Act: -0.1700
Data Index: 4861663 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2201. Min Act: -0.1700
Data Index: 1900221 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2201. Min Act: -0.1700
Data Index: 4477269 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8763. Min Range: -5.8763
Max Act: 5.2201. Min Act: -0.1700
Data Index: 2788630 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19