Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.7691. Min Act: -0.1700
Data Index: 2272273 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.7066. Min Act: -0.1700
Data Index: 7260943 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.5816. Min Act: -0.1700
Data Index: 5514751 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.5191. Min Act: -0.1700
Data Index: 8305963 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.4566. Min Act: -0.1700
Data Index: 6212531 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.4566. Min Act: -0.1700
Data Index: 4329757 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.3316. Min Act: -0.1700
Data Index: 1543806 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.3316. Min Act: -0.1700
Data Index: 1783693 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.3316. Min Act: -0.1700
Data Index: 568294 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2691. Min Act: -0.1700
Data Index: 5121941 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2691. Min Act: -0.1700
Data Index: 3152544 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2691. Min Act: -0.1700
Data Index: 3024896 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.3316. Min Act: -0.1700
Data Index: 4944443 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2066. Min Act: -0.1700
Data Index: 1137862 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2066. Min Act: -0.1700
Data Index: 1960731 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2066. Min Act: -0.1699
Data Index: 705952 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.2066. Min Act: -0.1700
Data Index: 7692869 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.1441. Min Act: -0.1700
Data Index: 2988396 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.1441. Min Act: -0.1700
Data Index: 2363594 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7691. Min Range: -10.7691
Max Act: 10.0816. Min Act: -0.1700
Data Index: 339377 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19