Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 4044260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 4244061 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 411814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 6844761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8323631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8375785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 8384992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 8665126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 8776400 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 2222124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1231638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5533. Min Act: -0.1700
Data Index: 546761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1922265 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1783655 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1633469 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.4906. Min Act: -0.1700
Data Index: 1387205 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 75126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 268440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.4906. Min Act: -0.1700
Data Index: 607804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5533. Min Range: -3.5533
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1065908 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19