Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.7324. Min Act: -0.1700
Data Index: 2556340 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.7012. Min Act: -0.1700
Data Index: 3589323 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.6387. Min Act: -0.1700
Data Index: 2411567 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.6074. Min Act: -0.1700
Data Index: 6876642 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.6074. Min Act: -0.1700
Data Index: 6646799 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.6074. Min Act: -0.1700
Data Index: 2884180 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.5762. Min Act: -0.1700
Data Index: 4856275 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.5137. Min Act: -0.1700
Data Index: 5128960 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.5449. Min Act: -0.1700
Data Index: 5169259 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.5137. Min Act: -0.1700
Data Index: 7258616 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4824. Min Act: -0.1700
Data Index: 7258795 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4824. Min Act: -0.1700
Data Index: 3451809 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4824. Min Act: -0.1700
Data Index: 1251807 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.5137. Min Act: -0.1700
Data Index: 987486 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4824. Min Act: -0.1700
Data Index: 5938226 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4512. Min Act: -0.1700
Data Index: 6531122 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4512. Min Act: -0.1700
Data Index: 6766166 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4199. Min Act: -0.1700
Data Index: 1027787 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4512. Min Act: -0.1700
Data Index: 1340192 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7324. Min Range: -4.7324
Max Act: 4.4199. Min Act: -0.1700
Data Index: 3294345 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19