Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0509. Min Range: -5.0509
Max Act: 5.0509. Min Act: -0.1700
Data Index: 4455065 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0509. Min Range: -5.0509
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6372208 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7742882 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7542220 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5593300 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7123363 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9259. Min Act: -0.1700
Data Index: 587157 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.9259. Min Act: -0.1700
Data Index: 2198452 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6148043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8946. Min Act: -0.1700
Data Index: 5956462 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8634. Min Act: -0.1700
Data Index: 1096134 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8634. Min Act: -0.1700
Data Index: 2906739 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8321. Min Act: -0.1700
Data Index: 4427785 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8634. Min Act: -0.1700
Data Index: 621468 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7243544 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8321. Min Act: -0.1700
Data Index: 8723579 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8009. Min Act: -0.1700
Data Index: 1303255 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2232299 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3863410 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0509. Min Range: -5.0509
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6355522 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19