Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5044 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.7103. Min Act: -0.1700
Data Index: 8519529 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.7103. Min Act: -0.1700
Data Index: 4160023 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6943. Min Act: -0.1700
Data Index: 5361532 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6783. Min Act: -0.1700
Data Index: 1386227 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6783. Min Act: -0.1700
Data Index: 1333314 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6783. Min Act: -0.1700
Data Index: 177651 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6623. Min Act: -0.1700
Data Index: 7496122 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6623. Min Act: -0.1700
Data Index: 396923 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6623. Min Act: -0.1700
Data Index: 8156190 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6623. Min Act: -0.1700
Data Index: 1384595 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6623. Min Act: -0.1700
Data Index: 4098694 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 1647905 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 350315 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 5781784 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 2235871 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 4866641 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6462. Min Act: -0.1700
Data Index: 4293655 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6302. Min Act: -0.1700
Data Index: 6112741 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6302. Min Act: -0.1700
Data Index: 3126284 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7103. Min Range: -2.7103
Max Act: 2.6302. Min Act: -0.1700
Data Index: 455552 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19