Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1771. Min Range: -6.1771
Max Act: 6.1771. Min Act: -0.1700
Data Index: 719714 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1771. Min Range: -6.1771
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6258451 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.8333. Min Act: -0.1700
Data Index: 6016984 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.8021. Min Act: -0.1700
Data Index: 8770534 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.7708. Min Act: -0.1700
Data Index: 7216813 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.7396. Min Act: -0.1700
Data Index: 3399006 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.7083. Min Act: -0.1700
Data Index: 8591867 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.7083. Min Act: -0.1700
Data Index: 6742722 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4274109 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3843218 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6771. Min Act: -0.1700
Data Index: 52361 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6458. Min Act: -0.1700
Data Index: 5484931 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6146. Min Act: -0.1700
Data Index: 797752 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6458. Min Act: -0.1700
Data Index: 6867921 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6458. Min Act: -0.1700
Data Index: 7177166 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.5833. Min Act: -0.1700
Data Index: 3935372 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6146. Min Act: -0.1700
Data Index: 7516969 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5786731 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.6146. Min Act: -0.1700
Data Index: 3236142 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1771. Min Range: -6.1771
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5380156 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19