Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 960 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0094. Min Range: -3.0094
Max Act: 3.0094. Min Act: -0.1696
Data Index: 5533277 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.9936. Min Act: -0.1700
Data Index: 5533276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.9145. Min Act: -0.1700
Data Index: 7641846 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 7714067 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 7280063 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 6965955 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 5850260 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 583705 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8669. Min Act: -0.1700
Data Index: 2748192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8510. Min Act: -0.1700
Data Index: 6041269 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8510. Min Act: -0.1700
Data Index: 6074874 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 6146057 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 6627351 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 6779645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 4274909 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 4691443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 1727810 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 5000889 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 1053116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0094. Min Range: -3.0094
Max Act: 2.8351. Min Act: -0.1700
Data Index: 3164569 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19