Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6282 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9904. Min Act: -0.1700
Data Index: 6781735 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.9279. Min Act: -0.1700
Data Index: 737000 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8967. Min Act: -0.1700
Data Index: 3938651 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8654. Min Act: -0.1700
Data Index: 4242907 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8654. Min Act: -0.1700
Data Index: 615568 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8342. Min Act: -0.1700
Data Index: 5320920 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8342. Min Act: -0.1700
Data Index: 390580 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8342. Min Act: -0.1700
Data Index: 7003176 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8342. Min Act: -0.1700
Data Index: 1161682 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 1616354 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 6805410 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 5725526 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8342. Min Act: -0.1700
Data Index: 2009012 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.8029. Min Act: -0.1700
Data Index: 3596858 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7717. Min Act: -0.1700
Data Index: 6450131 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7717. Min Act: -0.1700
Data Index: 4082613 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7717. Min Act: -0.1700
Data Index: 2295260 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7717. Min Act: -0.1700
Data Index: 5348097 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7717. Min Act: -0.1700
Data Index: 2921922 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9904. Min Range: -4.9904
Max Act: 4.7404. Min Act: -0.1700
Data Index: 627330 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19