Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.7176. Min Act: -0.1700
Data Index: 4531803 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.5926. Min Act: -0.1700
Data Index: 8484618 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.5926. Min Act: -0.1700
Data Index: 4730016 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.5614. Min Act: -0.1700
Data Index: 8482726 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.5614. Min Act: -0.1700
Data Index: 8240672 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.5614. Min Act: -0.1700
Data Index: 8627463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4676. Min Act: -0.1700
Data Index: 491306 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4989. Min Act: -0.1700
Data Index: 5149554 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4364. Min Act: -0.1700
Data Index: 2431055 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4676. Min Act: -0.1700
Data Index: 6973355 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4364. Min Act: -0.1700
Data Index: 3279435 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4364. Min Act: -0.1700
Data Index: 474789 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.4051. Min Act: -0.1700
Data Index: 897369 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.3426. Min Act: -0.1700
Data Index: 5954561 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.3426. Min Act: -0.1700
Data Index: 5226834 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.3426. Min Act: -0.1700
Data Index: 1642111 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.2489. Min Act: -0.1700
Data Index: 5939671 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.2801. Min Act: -0.1700
Data Index: 7498688 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.2489. Min Act: -0.1700
Data Index: 6234563 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7176. Min Range: -7.7176
Max Act: 7.2176. Min Act: -0.1700
Data Index: 432309 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19