Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.2643. Min Act: -0.1700
Data Index: 4807631 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.2014. Min Act: -0.1700
Data Index: 4709760 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.1542. Min Act: -0.1700
Data Index: 2137103 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.1699. Min Act: -0.1700
Data Index: 2153353 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0912. Min Act: -0.1700
Data Index: 5180478 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0912. Min Act: -0.1700
Data Index: 2693148 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0754. Min Act: -0.1700
Data Index: 4467518 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0439. Min Act: -0.1700
Data Index: 6750200 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0281. Min Act: -0.1700
Data Index: 1242797 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0281. Min Act: -0.1700
Data Index: 3545021 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0281. Min Act: -0.1700
Data Index: 8408698 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2643. Min Range: -3.2643
Max Act: 3.0123. Min Act: -0.1700
Data Index: 7983154 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9965. Min Act: -0.1700
Data Index: 7880999 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9965. Min Act: -0.1700
Data Index: 7772275 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9965. Min Act: -0.1700
Data Index: 6522847 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9965. Min Act: -0.1700
Data Index: 536260 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9807. Min Act: -0.1700
Data Index: 6245958 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9807. Min Act: -0.1700
Data Index: 687186 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9807. Min Act: -0.1700
Data Index: 3153384 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2643. Min Range: -3.2643
Max Act: 2.9807. Min Act: -0.1700
Data Index: 1524331 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19