Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.6677. Min Act: -0.1700
Data Index: 6287007 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2174828 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.5427. Min Act: -0.1700
Data Index: 4832370 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4802. Min Act: -0.1700
Data Index: 4113177 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.5115. Min Act: -0.1700
Data Index: 8712708 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.5115. Min Act: -0.1700
Data Index: 4744161 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 5232545 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4802. Min Act: -0.1700
Data Index: 1698000 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4802. Min Act: -0.1700
Data Index: 949815 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 1600202 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 4035877 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 3712095 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4177. Min Act: -0.1700
Data Index: 7876572 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 6193626 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4177. Min Act: -0.1700
Data Index: 3242962 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 5966023 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4490. Min Act: -0.1700
Data Index: 5676934 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4177. Min Act: -0.1700
Data Index: 7274736 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4177. Min Act: -0.1700
Data Index: 6608355 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6677. Min Range: -5.6677
Max Act: 5.4177. Min Act: -0.1700
Data Index: 2496346 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19