Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.4736. Min Act: -0.1700
Data Index: 4343642 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2861. Min Act: -0.1700
Data Index: 7147860 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 1693680 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.0986. Min Act: -0.1700
Data Index: 1523152 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8798. Min Act: -0.1700
Data Index: 2411060 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8798. Min Act: -0.1700
Data Index: 332865 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8798. Min Act: -0.1700
Data Index: 3523206 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8486. Min Act: -0.1700
Data Index: 8767658 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8173. Min Act: -0.1700
Data Index: 4945064 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.8173. Min Act: -0.1700
Data Index: 8555407 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.7861. Min Act: -0.1700
Data Index: 7316460 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.7861. Min Act: -0.1700
Data Index: 344148 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5508578 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5664290 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6611. Min Act: -0.1700
Data Index: 6341008 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6298. Min Act: -0.1700
Data Index: 548896 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6298. Min Act: -0.1700
Data Index: 6448926 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.6298. Min Act: -0.1700
Data Index: 5840629 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.5673. Min Act: -0.1700
Data Index: 2894126 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4736. Min Range: -6.4736
Max Act: 5.5986. Min Act: -0.1700
Data Index: 1218551 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19