Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6123. Min Range: -6.6123
Max Act: 6.6123. Min Act: -0.1700
Data Index: 1585578 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6123. Min Range: -6.6123
Max Act: 6.2060. Min Act: -0.1700
Data Index: 7944612 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6123. Min Range: -6.6123
Max Act: 6.1748. Min Act: -0.1700
Data Index: 6634575 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6123. Min Range: -6.6123
Max Act: 6.0498. Min Act: -0.1700
Data Index: 3891288 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.9873. Min Act: -0.1700
Data Index: 4688097 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.9248. Min Act: -0.1700
Data Index: 2806386 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8935. Min Act: -0.1700
Data Index: 269275 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8935. Min Act: -0.1700
Data Index: 3955112 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8935. Min Act: -0.1700
Data Index: 5050003 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8623. Min Act: -0.1700
Data Index: 2457751 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4448370 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8623. Min Act: -0.1700
Data Index: 2137125 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8310. Min Act: -0.1700
Data Index: 5092771 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8310. Min Act: -0.1700
Data Index: 785593 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8310. Min Act: -0.1700
Data Index: 2510825 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.8310. Min Act: -0.1700
Data Index: 3126834 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.7685. Min Act: -0.1700
Data Index: 6193380 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.7998. Min Act: -0.1700
Data Index: 3249903 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.7998. Min Act: -0.1700
Data Index: 1550264 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6123. Min Range: -6.6123
Max Act: 5.7998. Min Act: -0.1700
Data Index: 7189445 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19