Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0203. Min Range: -7.0203
Max Act: 7.0203. Min Act: -0.1700
Data Index: 2207678 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.9578. Min Act: -0.1700
Data Index: 3259893 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.8640. Min Act: -0.1700
Data Index: 672943 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.8015. Min Act: -0.1700
Data Index: 2641874 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.8015. Min Act: -0.1700
Data Index: 2375560 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7703. Min Act: -0.1700
Data Index: 7775038 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7703. Min Act: -0.1700
Data Index: 8122166 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7390. Min Act: -0.1700
Data Index: 7501108 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7703. Min Act: -0.1700
Data Index: 2794829 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7078. Min Act: -0.1700
Data Index: 4172566 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6378653 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7078. Min Act: -0.1700
Data Index: 7884393 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6765. Min Act: -0.1700
Data Index: 7683202 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6765. Min Act: -0.1700
Data Index: 2692189 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7078. Min Act: -0.1700
Data Index: 514452 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6453. Min Act: -0.1700
Data Index: 1662526 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6765. Min Act: -0.1700
Data Index: 8163002 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6453. Min Act: -0.1700
Data Index: 4580639 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6453. Min Act: -0.1700
Data Index: 2101928 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6140. Min Act: -0.1700
Data Index: 1724108 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19