Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1593 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.3552. Min Act: -0.1700
Data Index: 1369215 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.2927. Min Act: -0.1700
Data Index: 3128962 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.3552. Min Act: -0.1700
Data Index: 855097 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.2302. Min Act: -0.1700
Data Index: 1883061 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.1365. Min Act: -0.1700
Data Index: 8326966 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.0740. Min Act: -0.1700
Data Index: 3900969 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.1365. Min Act: -0.1700
Data Index: 4788027 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.0740. Min Act: -0.1700
Data Index: 4139219 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.0427. Min Act: -0.1700
Data Index: 1221341 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3552. Min Range: -6.3552
Max Act: 6.0115. Min Act: -0.1700
Data Index: 7425971 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.9177. Min Act: -0.1700
Data Index: 5040022 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2499458 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.8552. Min Act: -0.1700
Data Index: 5946336 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7927. Min Act: -0.1700
Data Index: 4274890 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.8240. Min Act: -0.1700
Data Index: 3116772 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7927. Min Act: -0.1700
Data Index: 7520129 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7615. Min Act: -0.1700
Data Index: 2961472 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7302. Min Act: -0.1700
Data Index: 8595046 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7302. Min Act: -0.1700
Data Index: 815601 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3552. Min Range: -6.3552
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5768123 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19