Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.8961. Min Act: -0.1700
Data Index: 4194531 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.7086. Min Act: -0.1700
Data Index: 6518297 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.7399. Min Act: -0.1700
Data Index: 1650191 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.7399. Min Act: -0.1700
Data Index: 258117 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.7086. Min Act: -0.1700
Data Index: 2803947 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.7086. Min Act: -0.1700
Data Index: 1911492 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6773. Min Act: -0.1700
Data Index: 4407986 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6773. Min Act: -0.1700
Data Index: 226676 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6461. Min Act: -0.1700
Data Index: 6426667 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6773. Min Act: -0.1700
Data Index: 7981522 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6773. Min Act: -0.1700
Data Index: 8102380 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6461. Min Act: -0.1700
Data Index: 6718602 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.5836. Min Act: -0.1700
Data Index: 6660458 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6461. Min Act: -0.1700
Data Index: 6671109 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6148. Min Act: -0.1700
Data Index: 3276024 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.5523. Min Act: -0.1700
Data Index: 6426678 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.5836. Min Act: -0.1700
Data Index: 3082397 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.5836. Min Act: -0.1700
Data Index: 349117 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.5836. Min Act: -0.1700
Data Index: 2748085 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8961. Min Range: -4.8961
Max Act: 4.6148. Min Act: -0.1700
Data Index: 6673335 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19