Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.5667. Min Act: -0.1700
Data Index: 8219141 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.3787. Min Act: -0.1700
Data Index: 2093857 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.2688. Min Act: -0.1700
Data Index: 6534895 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.2374. Min Act: -0.1700
Data Index: 6774906 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.2217. Min Act: -0.1700
Data Index: 5023464 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.2060. Min Act: -0.1700
Data Index: 1070551 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1588. Min Act: -0.1700
Data Index: 2012294 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1430. Min Act: -0.1700
Data Index: 2668058 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1588. Min Act: -0.1700
Data Index: 7442489 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1588. Min Act: -0.1700
Data Index: 263431 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1430. Min Act: -0.1700
Data Index: 5920624 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1430. Min Act: -0.1700
Data Index: 3040271 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1430. Min Act: -0.1700
Data Index: 3951103 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1273. Min Act: -0.1700
Data Index: 8241115 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1115. Min Act: -0.1700
Data Index: 427805 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.1115. Min Act: -0.1700
Data Index: 8449828 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.0800. Min Act: -0.1700
Data Index: 6611203 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.0800. Min Act: -0.1700
Data Index: 1946107 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.0642. Min Act: -0.1700
Data Index: 5669018 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5667. Min Range: -3.5667
Max Act: 3.0800. Min Act: -0.1700
Data Index: 7537619 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19