Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8972. Min Act: -0.1700
Data Index: 2072966 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8972. Min Act: -0.1700
Data Index: 7691692 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8347. Min Act: -0.1700
Data Index: 4553218 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8660. Min Act: -0.1700
Data Index: 3846141 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8347. Min Act: -0.1700
Data Index: 1811455 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8347. Min Act: -0.1700
Data Index: 5812109 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8035. Min Act: -0.1700
Data Index: 7100382 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8035. Min Act: -0.1700
Data Index: 3770633 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8035. Min Act: -0.1700
Data Index: 3770631 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5812111 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3770634 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 6332495 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 8287185 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 2168460 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 2168459 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7722. Min Act: -0.1700
Data Index: 7675629 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7410. Min Act: -0.1700
Data Index: 5173378 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7410. Min Act: -0.1700
Data Index: 1757770 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7410. Min Act: -0.1700
Data Index: 270716 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8972. Min Range: -5.8972
Max Act: 5.7097. Min Act: -0.1700
Data Index: 469969 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19