Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2242 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.6768. Min Act: -0.1700
Data Index: 1717450 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.4581. Min Act: -0.1700
Data Index: 8177866 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.4268. Min Act: -0.1700
Data Index: 2513572 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.4268. Min Act: -0.1700
Data Index: 1834382 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3331. Min Act: -0.1700
Data Index: 785296 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3643. Min Act: -0.1700
Data Index: 6276447 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2706. Min Act: -0.1700
Data Index: 6843983 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3331. Min Act: -0.1700
Data Index: 2854755 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 570367 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 8475396 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 7570867 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3331. Min Act: -0.1700
Data Index: 5714064 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 6721279 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2706. Min Act: -0.1700
Data Index: 2368637 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2706. Min Act: -0.1700
Data Index: 6206128 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2393. Min Act: -0.1700
Data Index: 8464057 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 7955686 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.3018. Min Act: -0.1700
Data Index: 704568 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2081. Min Act: -0.1700
Data Index: 8318783 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6768. Min Range: -6.6768
Max Act: 6.2393. Min Act: -0.1700
Data Index: 3330905 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19