Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1096. Min Range: -4.1096
Max Act: 4.1096. Min Act: -0.1700
Data Index: 5799341 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1096. Min Range: -4.1096
Max Act: 4.0783. Min Act: -0.1700
Data Index: 1738603 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1096. Min Range: -4.1096
Max Act: 4.0158. Min Act: -0.1700
Data Index: 2790015 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.9845. Min Act: -0.1700
Data Index: 3341205 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.9220. Min Act: -0.1700
Data Index: 2087069 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.9064. Min Act: -0.1700
Data Index: 6099430 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8908. Min Act: -0.1700
Data Index: 5665661 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8595. Min Act: -0.1700
Data Index: 5761115 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8595. Min Act: -0.1700
Data Index: 7514381 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8439. Min Act: -0.1700
Data Index: 2991018 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8282. Min Act: -0.1700
Data Index: 4285803 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8282. Min Act: -0.1700
Data Index: 1716011 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.8282. Min Act: -0.1700
Data Index: 5394188 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7969. Min Act: -0.1700
Data Index: 1781154 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7969. Min Act: -0.1700
Data Index: 7534032 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7813. Min Act: -0.1700
Data Index: 8101149 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7657. Min Act: -0.1700
Data Index: 4454106 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7500. Min Act: -0.1700
Data Index: 4735981 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7657. Min Act: -0.1700
Data Index: 2639993 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1096. Min Range: -4.1096
Max Act: 3.7657. Min Act: -0.1700
Data Index: 1202169 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19