Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 374 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.6023. Min Act: -0.1700
Data Index: 1732553 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.5086. Min Act: -0.1700
Data Index: 5777461 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.5086. Min Act: -0.1700
Data Index: 3404893 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.4773. Min Act: -0.1700
Data Index: 4839051 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.4773. Min Act: -0.1700
Data Index: 664703 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.4148. Min Act: -0.1700
Data Index: 4220775 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3918064 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.3211. Min Act: -0.1700
Data Index: 4861281 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.3523. Min Act: -0.1700
Data Index: 3298613 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.3523. Min Act: -0.1700
Data Index: 1949516 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.3523. Min Act: -0.1700
Data Index: 263429 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2898. Min Act: -0.1700
Data Index: 6427795 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2898. Min Act: -0.1700
Data Index: 6830203 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2586. Min Act: -0.1700
Data Index: 6444319 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2520683 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2586. Min Act: -0.1700
Data Index: 659696 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2858062 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.1961. Min Act: -0.1700
Data Index: 5431977 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2857390 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6023. Min Range: -5.6023
Max Act: 5.1961. Min Act: -0.1700
Data Index: 3239400 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19