Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.3829. Min Act: -0.1700
Data Index: 7651565 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.2267. Min Act: -0.1700
Data Index: 2094003 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.0392. Min Act: -0.1700
Data Index: 6233245 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.9454. Min Act: -0.1700
Data Index: 1067273 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3829. Min Range: -6.3829
Max Act: 6.0079. Min Act: -0.1700
Data Index: 6166187 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6954. Min Act: -0.1700
Data Index: 5856550 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6954. Min Act: -0.1700
Data Index: 1671827 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6954. Min Act: -0.1700
Data Index: 7986689 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6642. Min Act: -0.1700
Data Index: 7894885 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 8284318 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6017. Min Act: -0.1700
Data Index: 163176 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1026835 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6954. Min Act: -0.1700
Data Index: 5801922 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 3213834 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6017. Min Act: -0.1700
Data Index: 2145630 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1846628 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6017. Min Act: -0.1700
Data Index: 3892169 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6329. Min Act: -0.1700
Data Index: 3240451 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6017. Min Act: -0.1700
Data Index: 1026826 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3829. Min Range: -6.3829
Max Act: 5.6017. Min Act: -0.1700
Data Index: 4679100 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19