Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5500. Min Act: -0.1700
Data Index: 6476628 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5500. Min Act: -0.1700
Data Index: 403591 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5500. Min Act: -0.1700
Data Index: 2738399 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5500. Min Act: -0.1700
Data Index: 1517091 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5500. Min Act: -0.1700
Data Index: 2068030 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5187. Min Act: -0.1700
Data Index: 2319655 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5187. Min Act: -0.1700
Data Index: 4922080 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4875. Min Act: -0.1700
Data Index: 3951411 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4875. Min Act: -0.1700
Data Index: 37662 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4562. Min Act: -0.1700
Data Index: 4053922 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.5187. Min Act: -0.1700
Data Index: 2276809 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4562. Min Act: -0.1700
Data Index: 3923989 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4562. Min Act: -0.1700
Data Index: 8062221 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2819465 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4454700 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4887119 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 2838725 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 5039885 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 5446205 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5500. Min Range: -5.5500
Max Act: 5.3937. Min Act: -0.1700
Data Index: 977087 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19