Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4751. Min Act: -0.1700
Data Index: 2738181 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4487. Min Act: -0.1700
Data Index: 7932029 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4399. Min Act: -0.1700
Data Index: 1924010 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4311. Min Act: -0.1700
Data Index: 4290504 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4223. Min Act: -0.1700
Data Index: 1707510 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4047. Min Act: -0.1700
Data Index: 1615561 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4135. Min Act: -0.1700
Data Index: 1014708 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.4047. Min Act: -0.1700
Data Index: 3981220 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3871. Min Act: -0.1700
Data Index: 6666668 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3871. Min Act: -0.1700
Data Index: 7673049 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3782. Min Act: -0.1700
Data Index: 3004437 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3782. Min Act: -0.1700
Data Index: 5813387 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3959. Min Act: -0.1697
Data Index: 606513 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3871. Min Act: -0.1700
Data Index: 6176481 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3782. Min Act: -0.1700
Data Index: 3800317 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3782. Min Act: -0.1699
Data Index: 7751481 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3694. Min Act: -0.1700
Data Index: 4222404 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3606. Min Act: -0.1700
Data Index: 4862767 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3694. Min Act: -0.1699
Data Index: 7690138 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4751. Min Range: -1.4751
Max Act: 1.3694. Min Act: -0.1700
Data Index: 7101146 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19