Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.6356. Min Act: -0.1700
Data Index: 7171199 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.6043. Min Act: -0.1700
Data Index: 8498190 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.5731. Min Act: -0.1700
Data Index: 6954029 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.5418. Min Act: -0.1700
Data Index: 1337150 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4481. Min Act: -0.1700
Data Index: 2875306 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4481. Min Act: -0.1700
Data Index: 1785590 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4481. Min Act: -0.1700
Data Index: 8103918 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3856. Min Act: -0.1700
Data Index: 4376529 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3634940 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.4168. Min Act: -0.1700
Data Index: 7986510 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 3224426 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2401758 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 8592545 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3231. Min Act: -0.1700
Data Index: 4804219 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 7594449 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3231. Min Act: -0.1700
Data Index: 5726260 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4705296 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3543. Min Act: -0.1700
Data Index: 6135175 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.3231. Min Act: -0.1700
Data Index: 2991877 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6356. Min Range: -6.6356
Max Act: 6.2918. Min Act: -0.1700
Data Index: 6504888 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19