Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.7877. Min Act: -0.1700
Data Index: 7444406 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6315. Min Act: -0.1700
Data Index: 7921160 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6315. Min Act: -0.1700
Data Index: 8227277 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6315. Min Act: -0.1700
Data Index: 3998721 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6315. Min Act: -0.1700
Data Index: 5463208 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6315. Min Act: -0.1700
Data Index: 1452705 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6002. Min Act: -0.1700
Data Index: 6943569 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.6002. Min Act: -0.1700
Data Index: 5895532 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.5690. Min Act: -0.1700
Data Index: 6838772 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.5377. Min Act: -0.1700
Data Index: 6079784 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.5065. Min Act: -0.1700
Data Index: 1795683 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.5065. Min Act: -0.1700
Data Index: 5347623 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.5065. Min Act: -0.1700
Data Index: 2046665 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4752. Min Act: -0.1700
Data Index: 6360872 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4752. Min Act: -0.1700
Data Index: 2410544 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4752. Min Act: -0.1700
Data Index: 4769509 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4752. Min Act: -0.1700
Data Index: 4101958 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4440. Min Act: -0.1700
Data Index: 2194056 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4440. Min Act: -0.1700
Data Index: 1722719 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7877. Min Range: -4.7877
Max Act: 4.4440. Min Act: -0.1700
Data Index: 7492826 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19