Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1148 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3252. Min Range: -10.3252
Max Act: 10.3252. Min Act: -0.1700
Data Index: 2553209 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.8877. Min Act: -0.1700
Data Index: 1403878 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.8252. Min Act: -0.1700
Data Index: 1055959 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.7627. Min Act: -0.1700
Data Index: 2386814 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.7002. Min Act: -0.1700
Data Index: 6064179 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.7002. Min Act: -0.1700
Data Index: 7048157 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.7002. Min Act: -0.1700
Data Index: 3838161 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.6377. Min Act: -0.1700
Data Index: 4140463 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.5752. Min Act: -0.1700
Data Index: 5204213 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.6377. Min Act: -0.1700
Data Index: 8822504 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.5127. Min Act: -0.1700
Data Index: 4051584 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.5127. Min Act: -0.1700
Data Index: 2681149 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.4502. Min Act: -0.1700
Data Index: 5882570 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3877. Min Act: -0.1700
Data Index: 1147659 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3877. Min Act: -0.1700
Data Index: 7865872 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3877. Min Act: -0.1700
Data Index: 7447509 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3252. Min Act: -0.1700
Data Index: 5391766 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3252. Min Act: -0.1700
Data Index: 2135381 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3252. Min Act: -0.1700
Data Index: 2409227 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3252. Min Range: -10.3252
Max Act: 9.3252. Min Act: -0.1700
Data Index: 2958849 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19