Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0092. Min Range: -5.0092
Max Act: 5.0092. Min Act: -0.1700
Data Index: 5469611 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8842. Min Act: -0.1700
Data Index: 6638544 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2694549 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8529. Min Act: -0.1700
Data Index: 6414624 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 3894239 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2999173 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2151677 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 7332150 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2583761 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7904. Min Act: -0.1700
Data Index: 7513386 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7904. Min Act: -0.1700
Data Index: 4045350 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7904. Min Act: -0.1700
Data Index: 5145970 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7904. Min Act: -0.1700
Data Index: 7856236 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 2732338 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 3840184 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 1240834 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 8038176 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 6781027 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 4221260 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0092. Min Range: -5.0092
Max Act: 4.7592. Min Act: -0.1700
Data Index: 2154345 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19