Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 349 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1311. Min Range: -5.1311
Max Act: 5.1311. Min Act: -0.1700
Data Index: 838498 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1311. Min Range: -5.1311
Max Act: 5.1311. Min Act: -0.1700
Data Index: 759343 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1311. Min Range: -5.1311
Max Act: 5.0686. Min Act: -0.1700
Data Index: 4105575 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1311. Min Range: -5.1311
Max Act: 5.0374. Min Act: -0.1700
Data Index: 5966541 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9749. Min Act: -0.1700
Data Index: 7666407 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9436. Min Act: -0.1700
Data Index: 3901692 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9749. Min Act: -0.1700
Data Index: 8779271 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9124. Min Act: -0.1700
Data Index: 5670516 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9436. Min Act: -0.1700
Data Index: 3470808 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.9124. Min Act: -0.1700
Data Index: 6702002 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 350949 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8811. Min Act: -0.1700
Data Index: 6636751 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 4615294 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8811. Min Act: -0.1700
Data Index: 4465812 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 2378341 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8811. Min Act: -0.1700
Data Index: 5369793 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 1143518 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 5727016 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8811. Min Act: -0.1700
Data Index: 4752371 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1311. Min Range: -5.1311
Max Act: 4.8499. Min Act: -0.1700
Data Index: 4756632 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19