Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.9262. Min Act: -0.1700
Data Index: 1153562 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.8949. Min Act: -0.1700
Data Index: 5695273 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.8949. Min Act: -0.1700
Data Index: 4076491 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.8324. Min Act: -0.1700
Data Index: 8505968 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.8012. Min Act: -0.1700
Data Index: 7863282 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.8012. Min Act: -0.1700
Data Index: 70661 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.7387. Min Act: -0.1700
Data Index: 3724520 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.7074. Min Act: -0.1700
Data Index: 1321754 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6449. Min Act: -0.1700
Data Index: 8683398 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.7074. Min Act: -0.1700
Data Index: 7425622 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5470631 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6137. Min Act: -0.1700
Data Index: 755772 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6137. Min Act: -0.1700
Data Index: 8760771 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6449. Min Act: -0.1700
Data Index: 3045392 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.6137. Min Act: -0.1700
Data Index: 3519357 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.5824. Min Act: -0.1700
Data Index: 3752468 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.5824. Min Act: -0.1700
Data Index: 4636672 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.5824. Min Act: -0.1700
Data Index: 551634 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.5512. Min Act: -0.1700
Data Index: 6654530 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9262. Min Range: -4.9262
Max Act: 4.5199. Min Act: -0.1700
Data Index: 1551457 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19