Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.6291. Min Act: -0.1700
Data Index: 1537317 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.6291. Min Act: -0.1700
Data Index: 1690875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.6291. Min Act: -0.1700
Data Index: 1906563 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.6291. Min Act: -0.1700
Data Index: 6603252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5978. Min Act: -0.1700
Data Index: 8311899 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5978. Min Act: -0.1700
Data Index: 1764596 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 6373407 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 1352632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 1295879 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 1209143 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 4296545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 1540043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 979866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 3694824 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 5672975 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 951317 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 500724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 5222509 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 2270328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6291. Min Range: -3.6291
Max Act: 3.5665. Min Act: -0.1700
Data Index: 196021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19