Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6574. Min Act: -0.1700
Data Index: 1006456 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 1534465 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 7190405 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2218776 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 5807943 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 2021865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6376929 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 8016194 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 7506227 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6835496 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 1252378 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 547475 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 102203 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.6261. Min Act: -0.1700
Data Index: 6676472 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.5011. Min Act: -0.1700
Data Index: 1655588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.5011. Min Act: -0.1700
Data Index: 366203 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.5011. Min Act: -0.1700
Data Index: 6578923 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.4386. Min Act: -0.1700
Data Index: 3518208 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.4386. Min Act: -0.1700
Data Index: 8728118 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6574. Min Range: -5.6574
Max Act: 5.4386. Min Act: -0.1700
Data Index: 8331655 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19