Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2940. Min Act: -0.1700
Data Index: 7207705 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2940. Min Act: -0.1700
Data Index: 1612184 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2627. Min Act: -0.1700
Data Index: 8040986 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7515792 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2315. Min Act: -0.1700
Data Index: 1683189 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.2002. Min Act: -0.1700
Data Index: 2958121 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2940. Min Range: -7.2940
Max Act: 7.0752. Min Act: -0.1700
Data Index: 5005948 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.9502. Min Act: -0.1700
Data Index: 4450293 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.9190. Min Act: -0.1700
Data Index: 8179017 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.8565. Min Act: -0.1700
Data Index: 6395233 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.8565. Min Act: -0.1700
Data Index: 1996650 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.8252. Min Act: -0.1700
Data Index: 854194 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.8252. Min Act: -0.1700
Data Index: 7339429 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7940. Min Act: -0.1700
Data Index: 4009778 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7940. Min Act: -0.1700
Data Index: 492118 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7627. Min Act: -0.1700
Data Index: 4653842 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7315. Min Act: -0.1700
Data Index: 8797874 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7315. Min Act: -0.1700
Data Index: 551129 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7002. Min Act: -0.1700
Data Index: 1815188 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2940. Min Range: -7.2940
Max Act: 6.7002. Min Act: -0.1700
Data Index: 5626855 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19