Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 344 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0042. Min Range: -6.0042
Max Act: 6.0042. Min Act: -0.1700
Data Index: 4345677 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.8792. Min Act: -0.1700
Data Index: 5364298 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.7854. Min Act: -0.1700
Data Index: 6150552 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6604. Min Act: -0.1700
Data Index: 1181570 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6292. Min Act: -0.1700
Data Index: 349397 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6604. Min Act: -0.1700
Data Index: 3224943 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6292. Min Act: -0.1700
Data Index: 3988163 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6604. Min Act: -0.1700
Data Index: 4675995 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.6292. Min Act: -0.1700
Data Index: 3965094 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5979. Min Act: -0.1700
Data Index: 3532627 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5979. Min Act: -0.1699
Data Index: 2379252 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5833975 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2398059 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2841096 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5972232 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2783220 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5667. Min Act: -0.1700
Data Index: 998838 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5042. Min Act: -0.1700
Data Index: 100439 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5354. Min Act: -0.1700
Data Index: 2247315 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0042. Min Range: -6.0042
Max Act: 5.5354. Min Act: -0.1700
Data Index: 4667823 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19