Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.6937. Min Act: -0.1700
Data Index: 5739308 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.6624. Min Act: -0.1700
Data Index: 4643496 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.6312. Min Act: -0.1700
Data Index: 5706165 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5842. Min Act: -0.1700
Data Index: 6058965 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.6312. Min Act: -0.1700
Data Index: 4664226 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5685. Min Act: -0.1700
Data Index: 966003 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5842. Min Act: -0.1700
Data Index: 746453 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5529. Min Act: -0.1700
Data Index: 830108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5529. Min Act: -0.1700
Data Index: 957356 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5059. Min Act: -0.1700
Data Index: 4709254 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4903. Min Act: -0.1700
Data Index: 5445592 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.5059. Min Act: -0.1700
Data Index: 500800 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7641655 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4746. Min Act: -0.1700
Data Index: 1947591 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4746. Min Act: -0.1700
Data Index: 4072767 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4746. Min Act: -0.1700
Data Index: 3729104 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4746. Min Act: -0.1700
Data Index: 6233390 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4903. Min Act: -0.1700
Data Index: 5780656 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4746. Min Act: -0.1700
Data Index: 8686418 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6937. Min Range: -3.6937
Max Act: 3.4589. Min Act: -0.1700
Data Index: 2021790 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19