Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2142 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5293241 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6711. Min Act: -0.1700
Data Index: 5781331 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6711. Min Act: -0.1700
Data Index: 692936 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6399. Min Act: -0.1700
Data Index: 875250 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6399. Min Act: -0.1700
Data Index: 6350062 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6711. Min Act: -0.1700
Data Index: 2911925 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6399. Min Act: -0.1700
Data Index: 5800648 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6539469 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5774. Min Act: -0.1700
Data Index: 5800649 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5461. Min Act: -0.1700
Data Index: 4614128 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5461. Min Act: -0.1700
Data Index: 2111021 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5461. Min Act: -0.1700
Data Index: 7141237 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5774. Min Act: -0.1700
Data Index: 7066853 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5149. Min Act: -0.1700
Data Index: 7830341 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5149. Min Act: -0.1700
Data Index: 194177 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5149. Min Act: -0.1700
Data Index: 840636 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5149. Min Act: -0.1700
Data Index: 1755415 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.5149. Min Act: -0.1700
Data Index: 5251865 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.4524. Min Act: -0.1700
Data Index: 5852536 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7961. Min Range: -5.7961
Max Act: 5.4836. Min Act: -0.1700
Data Index: 2193762 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19