Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4854 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.9760. Min Act: -0.1700
Data Index: 8407237 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.8822. Min Act: -0.1700
Data Index: 5509542 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 5773625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 6091091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 6427334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2665741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2581320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 4490773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1845754 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 900645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 3450858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 792753 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 876931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1516526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 5102332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1789714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 6408347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 3053802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 4097146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9760. Min Range: -4.9760
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2383755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19