Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.4182. Min Act: -0.1700
Data Index: 5264092 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.3245. Min Act: -0.1700
Data Index: 3863219 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2932. Min Act: -0.1700
Data Index: 683927 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 690540 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 2248945 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 2206136 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 88041 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 136815 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1545191 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 621675 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1419393 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1289613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1205525 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1123121 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 187937 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 1122547 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 2183545 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1699
Data Index: 1725862 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 177827 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4182. Min Range: -4.4182
Max Act: 4.2619. Min Act: -0.1700
Data Index: 153281 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19