Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.9597. Min Act: -0.1700
Data Index: 6509514 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.9284. Min Act: -0.1700
Data Index: 4850339 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8972. Min Act: -0.1700
Data Index: 6343221 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8972. Min Act: -0.1700
Data Index: 3900278 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8659. Min Act: -0.1700
Data Index: 1155481 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 5516687 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 672795 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8659. Min Act: -0.1700
Data Index: 1481741 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 7581009 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 7498197 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 1336501 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 7879208 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 5200615 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8034. Min Act: -0.1700
Data Index: 3799152 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8347. Min Act: -0.1700
Data Index: 8480747 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4426050 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.8034. Min Act: -0.1700
Data Index: 5953971 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7722. Min Act: -0.1700
Data Index: 5399033 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7722. Min Act: -0.1700
Data Index: 6945729 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9597. Min Range: -4.9597
Max Act: 4.7722. Min Act: -0.1700
Data Index: 490209 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19