Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0920. Min Range: -3.0920
Max Act: 3.0920. Min Act: -0.1700
Data Index: 4265473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0920. Min Range: -3.0920
Max Act: 3.0289. Min Act: -0.1700
Data Index: 955813 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0920. Min Range: -3.0920
Max Act: 3.0289. Min Act: -0.1700
Data Index: 59948 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0920. Min Range: -3.0920
Max Act: 3.0131. Min Act: -0.1700
Data Index: 5918577 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0920. Min Range: -3.0920
Max Act: 3.0131. Min Act: -0.1700
Data Index: 6632183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9499. Min Act: -0.1700
Data Index: 3739918 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9657. Min Act: -0.1700
Data Index: 3316393 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9657. Min Act: -0.1700
Data Index: 7217467 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9499. Min Act: -0.1700
Data Index: 8741428 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 1630529 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9341. Min Act: -0.1700
Data Index: 2136284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9341. Min Act: -0.1700
Data Index: 8198329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 3497984 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 1937499 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 3702401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 130308 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9182. Min Act: -0.1700
Data Index: 4530539 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9024. Min Act: -0.1700
Data Index: 870812 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.9024. Min Act: -0.1700
Data Index: 5127029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0920. Min Range: -3.0920
Max Act: 2.8706. Min Act: -0.1700
Data Index: 4398956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19