Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 431 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0103. Min Range: -4.0103
Max Act: 4.0103. Min Act: -0.1700
Data Index: 239809 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9791. Min Act: -0.1700
Data Index: 4807606 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9791. Min Act: -0.1700
Data Index: 7746237 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9791. Min Act: -0.1700
Data Index: 2209621 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9478. Min Act: -0.1700
Data Index: 2008627 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9478. Min Act: -0.1700
Data Index: 7869429 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9478. Min Act: -0.1700
Data Index: 7883704 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8853. Min Act: -0.1700
Data Index: 3973288 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.9165. Min Act: -0.1700
Data Index: 31571 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 3547407 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 18396 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 1115902 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 7464416 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8227. Min Act: -0.1700
Data Index: 1407878 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 4458110 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8540. Min Act: -0.1700
Data Index: 1334972 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8227. Min Act: -0.1700
Data Index: 4365196 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8227. Min Act: -0.1700
Data Index: 2862292 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8227. Min Act: -0.1700
Data Index: 5434357 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0103. Min Range: -4.0103
Max Act: 3.8227. Min Act: -0.1700
Data Index: 5290357 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19