Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2072474 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.5895. Min Act: -0.1700
Data Index: 894234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.5582. Min Act: -0.1700
Data Index: 4642985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.5269. Min Act: -0.1700
Data Index: 1702766 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4643. Min Act: -0.1700
Data Index: 3316154 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4643. Min Act: -0.1700
Data Index: 6598581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4643. Min Act: -0.1700
Data Index: 1114106 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4643. Min Act: -0.1700
Data Index: 8786013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4643. Min Act: -0.1700
Data Index: 5159335 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 5747534 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 2380954 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 5713419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 404226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 4237690 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4329. Min Act: -0.1700
Data Index: 4784458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4016. Min Act: -0.1699
Data Index: 5810688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4016. Min Act: -0.1700
Data Index: 3562966 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4016. Min Act: -0.1700
Data Index: 1845664 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.4016. Min Act: -0.1700
Data Index: 1858309 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6208. Min Range: -3.6208
Max Act: 3.3702. Min Act: -0.1700
Data Index: 4129812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19