Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.9662. Min Act: -0.1700
Data Index: 3662612 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.9349. Min Act: -0.1700
Data Index: 8106027 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8724. Min Act: -0.1700
Data Index: 2844691 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8724. Min Act: -0.1700
Data Index: 188090 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8724. Min Act: -0.1700
Data Index: 5475186 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8412. Min Act: -0.1700
Data Index: 4820521 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8412. Min Act: -0.1700
Data Index: 7815660 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 2025212 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8412. Min Act: -0.1700
Data Index: 8118721 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8412. Min Act: -0.1700
Data Index: 5374315 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 4881066 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 2729523 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 8554143 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 3804076 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 1282100 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 250867 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.8099. Min Act: -0.1700
Data Index: 3438446 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.7787. Min Act: -0.1700
Data Index: 5718278 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.7787. Min Act: -0.1700
Data Index: 2821339 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9662. Min Range: -5.9662
Max Act: 5.7787. Min Act: -0.1700
Data Index: 5848001 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19