Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.9533. Min Act: -0.1700
Data Index: 2332771 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.7971. Min Act: -0.1700
Data Index: 4827193 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.7346. Min Act: -0.1700
Data Index: 4732203 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.7658. Min Act: -0.1700
Data Index: 6848545 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.7033. Min Act: -0.1700
Data Index: 3543012 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6721. Min Act: -0.1700
Data Index: 5504498 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.7033. Min Act: -0.1700
Data Index: 3313905 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6721. Min Act: -0.1700
Data Index: 2669865 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6721. Min Act: -0.1700
Data Index: 4861885 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6408. Min Act: -0.1700
Data Index: 7644756 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6721. Min Act: -0.1700
Data Index: 1597949 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6408. Min Act: -0.1700
Data Index: 6359528 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6408. Min Act: -0.1700
Data Index: 1910877 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6408. Min Act: -0.1700
Data Index: 3417642 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.5783. Min Act: -0.1700
Data Index: 5290427 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5815577 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 4169194 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5815574 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 4488968 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9533. Min Range: -5.9533
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5414820 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19