Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2017. Min Range: -6.2017
Max Act: 6.2017. Min Act: -0.1700
Data Index: 6471637 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.9829. Min Act: -0.1700
Data Index: 5373538 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.6079. Min Act: -0.1700
Data Index: 5244912 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.5767. Min Act: -0.1700
Data Index: 2075527 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.6079. Min Act: -0.1700
Data Index: 2877015 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.4204. Min Act: -0.1700
Data Index: 708224 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.3579. Min Act: -0.1700
Data Index: 3922996 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.2954. Min Act: -0.1700
Data Index: 4326375 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.4517. Min Act: -0.1700
Data Index: 6004550 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.3579. Min Act: -0.1699
Data Index: 6162997 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.3267. Min Act: -0.1700
Data Index: 4213144 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.2954. Min Act: -0.1700
Data Index: 2519661 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6206605 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 1204780 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.2954. Min Act: -0.1700
Data Index: 6578906 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.2642. Min Act: -0.1700
Data Index: 3599121 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4585536 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 182300 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 3136686 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2017. Min Range: -6.2017
Max Act: 5.2329. Min Act: -0.1700
Data Index: 2515392 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19