Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2445. Min Act: -0.1700
Data Index: 1277647 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2445. Min Act: -0.1700
Data Index: 8796176 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3507876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1699
Data Index: 3246263 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 8275382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 4168333 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 8377557 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 6495480 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 87529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 4011947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 977175 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3358909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3316264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3854499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.2133. Min Act: -0.1698
Data Index: 1440682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.1820. Min Act: -0.1700
Data Index: 7751485 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.1820. Min Act: -0.1700
Data Index: 1328101 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.1508. Min Act: -0.1700
Data Index: 7618155 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.1508. Min Act: -0.1700
Data Index: 7841925 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2445. Min Range: -5.2445
Max Act: 5.1508. Min Act: -0.1700
Data Index: 3837608 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19