Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1787. Min Range: -4.1787
Max Act: 4.1787. Min Act: -0.1700
Data Index: 7869234 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1787. Min Range: -4.1787
Max Act: 4.0536. Min Act: -0.1700
Data Index: 2277636 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.9911. Min Act: -0.1700
Data Index: 7803725 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8661. Min Act: -0.1700
Data Index: 753881 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8973. Min Act: -0.1700
Data Index: 874821 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8661. Min Act: -0.1700
Data Index: 6130270 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8661. Min Act: -0.1700
Data Index: 4211795 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8348. Min Act: -0.1700
Data Index: 8686245 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8348. Min Act: -0.1700
Data Index: 1756549 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.8035. Min Act: -0.1700
Data Index: 2099623 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.7722. Min Act: -0.1700
Data Index: 2007706 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.7097. Min Act: -0.1700
Data Index: 1756548 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.7097. Min Act: -0.1700
Data Index: 3006378 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6784. Min Act: -0.1700
Data Index: 290313 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6471. Min Act: -0.1700
Data Index: 4951386 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.7097. Min Act: -0.1700
Data Index: 8448109 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6471. Min Act: -0.1700
Data Index: 721954 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6784. Min Act: -0.1700
Data Index: 4211801 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6471. Min Act: -0.1700
Data Index: 1283230 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1787. Min Range: -4.1787
Max Act: 3.6314. Min Act: -0.1700
Data Index: 5065030 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19