Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2372 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.6575. Min Act: -0.1700
Data Index: 6926838 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.3137. Min Act: -0.1700
Data Index: 6722938 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.2512. Min Act: -0.1700
Data Index: 7364268 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.2200. Min Act: -0.1700
Data Index: 2866516 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.1575. Min Act: -0.1700
Data Index: 5173212 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.1887. Min Act: -0.1700
Data Index: 5318576 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.1262. Min Act: -0.1700
Data Index: 4401525 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0950. Min Act: -0.1700
Data Index: 2255596 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0950. Min Act: -0.1700
Data Index: 804160 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0950. Min Act: -0.1700
Data Index: 1230723 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0950. Min Act: -0.1700
Data Index: 7269289 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0325. Min Act: -0.1700
Data Index: 6551955 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 3795663 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 6346254 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 2472182 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 8260917 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 1613471 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 3787468 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6575. Min Range: -6.6575
Max Act: 5.9700. Min Act: -0.1700
Data Index: 6468674 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6575. Min Range: -6.6575
Max Act: 6.0012. Min Act: -0.1700
Data Index: 2691548 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19