Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.9725. Min Act: -0.1700
Data Index: 8699723 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.9100. Min Act: -0.1700
Data Index: 8415037 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.9100. Min Act: -0.1700
Data Index: 3684385 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8787. Min Act: -0.1700
Data Index: 8723411 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8475. Min Act: -0.1700
Data Index: 7431890 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 1341563 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.8162. Min Act: -0.1700
Data Index: 62485 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 7032597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 4683013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7850. Min Act: -0.1700
Data Index: 715822 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7225. Min Act: -0.1700
Data Index: 532053 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7225. Min Act: -0.1700
Data Index: 1174518 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5203220 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.7537. Min Act: -0.1700
Data Index: 1174522 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6912. Min Act: -0.1700
Data Index: 4134758 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6912. Min Act: -0.1700
Data Index: 6851950 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6600. Min Act: -0.1700
Data Index: 19152 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1418644 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6600. Min Act: -0.1700
Data Index: 688750 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9725. Min Range: -4.9725
Max Act: 4.6600. Min Act: -0.1700
Data Index: 245978 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19