Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.8431. Min Act: -0.1700
Data Index: 413952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.8118. Min Act: -0.1700
Data Index: 6772401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.8118. Min Act: -0.1700
Data Index: 3250321 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 1724976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 6021537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 5396641 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 5011320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 4760895 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 7115338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 7041877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 6392758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 4682408 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.6867. Min Act: -0.1700
Data Index: 4854621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7493. Min Act: -0.1700
Data Index: 4408876 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.6867. Min Act: -0.1700
Data Index: 2816024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 1134699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 2839591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 2922364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 5738815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8431. Min Range: -3.8431
Max Act: 3.7180. Min Act: -0.1700
Data Index: 6278303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19