Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 116 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1699
Data Index: 7741019 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1698
Data Index: 8178014 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 2315552 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 7709459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 1154264 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 5918342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 5177379 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 1109097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 1121102 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1700
Data Index: 5725416 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9231. Min Act: -0.1700
Data Index: 763605 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9231. Min Act: -0.1700
Data Index: 6416807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9231. Min Act: -0.1700
Data Index: 5591232 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9231. Min Act: -0.1700
Data Index: 389394 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9543. Min Act: -0.1697
Data Index: 3995866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.9231. Min Act: -0.1700
Data Index: 2637133 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.8918. Min Act: -0.1700
Data Index: 689753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.8918. Min Act: -0.1700
Data Index: 2692677 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.8918. Min Act: -0.1700
Data Index: 1529018 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9543. Min Range: -3.9543
Max Act: 3.8918. Min Act: -0.1700
Data Index: 1759561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19