Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1389. Min Act: -0.1700
Data Index: 4293608 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1555. Min Act: -0.1700
Data Index: 5925047 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1222. Min Act: -0.1700
Data Index: 7640319 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1222. Min Act: -0.1700
Data Index: 5512026 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1222. Min Act: -0.1700
Data Index: 4430024 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1222. Min Act: -0.1700
Data Index: 6051804 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1222. Min Act: -0.1699
Data Index: 166543 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1054. Min Act: -0.1700
Data Index: 6529502 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1054. Min Act: -0.1700
Data Index: 6754456 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1054. Min Act: -0.1700
Data Index: 2157804 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 6707535 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1054. Min Act: -0.1700
Data Index: 146823 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 7851237 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1685
Data Index: 5079886 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 1581595 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.1054. Min Act: -0.1700
Data Index: 3717636 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 6383329 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 2410160 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 4017038 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1555. Min Range: -2.1555
Max Act: 2.0887. Min Act: -0.1700
Data Index: 7293677 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19