Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.4449. Min Act: -0.1700
Data Index: 5187760 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.2566. Min Act: -0.1700
Data Index: 2509926 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.1466. Min Act: -0.1700
Data Index: 4802940 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.0678. Min Act: -0.1700
Data Index: 5531023 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.0520. Min Act: -0.1700
Data Index: 4059979 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.0204. Min Act: -0.1700
Data Index: 6202683 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.0046. Min Act: -0.1700
Data Index: 1362088 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4449. Min Range: -3.4449
Max Act: 3.0046. Min Act: -0.1700
Data Index: 4488636 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.9414. Min Act: -0.1700
Data Index: 1459444 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.9255. Min Act: -0.1700
Data Index: 8184974 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.9097. Min Act: -0.1700
Data Index: 6855596 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.9097. Min Act: -0.1700
Data Index: 7149075 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8938. Min Act: -0.1700
Data Index: 1511807 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8779. Min Act: -0.1700
Data Index: 4802943 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8621. Min Act: -0.1700
Data Index: 711040 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8621. Min Act: -0.1700
Data Index: 1845518 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8462. Min Act: -0.1700
Data Index: 3018472 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8303. Min Act: -0.1700
Data Index: 6665940 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8303. Min Act: -0.1700
Data Index: 8032238 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4449. Min Range: -3.4449
Max Act: 2.8144. Min Act: -0.1700
Data Index: 7320005 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19