Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.8606. Min Act: -0.1700
Data Index: 6681573 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.7981. Min Act: -0.1700
Data Index: 1715178 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.7356. Min Act: -0.1700
Data Index: 3544701 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.7356. Min Act: -0.1700
Data Index: 6023022 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.7356. Min Act: -0.1700
Data Index: 2919903 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.7356. Min Act: -0.1700
Data Index: 2053531 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.6731. Min Act: -0.1700
Data Index: 6388534 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.6731. Min Act: -0.1700
Data Index: 4737616 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.5794. Min Act: -0.1700
Data Index: 3210954 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.5794. Min Act: -0.1700
Data Index: 6979096 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.5481. Min Act: -0.1700
Data Index: 4712797 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.5169. Min Act: -0.1700
Data Index: 8325133 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4856. Min Act: -0.1700
Data Index: 3036386 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4856. Min Act: -0.1700
Data Index: 6161128 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4856. Min Act: -0.1700
Data Index: 8232918 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4544. Min Act: -0.1700
Data Index: 2823154 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4231. Min Act: -0.1700
Data Index: 4156293 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4231. Min Act: -0.1700
Data Index: 1891966 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.4231. Min Act: -0.1700
Data Index: 206990 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8606. Min Range: -7.8606
Max Act: 7.3919. Min Act: -0.1700
Data Index: 1853056 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19