Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1498. Min Act: -0.1588
Data Index: 4061540 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1331. Min Act: -0.1700
Data Index: 8228912 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1331. Min Act: -0.1677
Data Index: 4961188 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1331. Min Act: -0.1695
Data Index: 4349785 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1164. Min Act: -0.1699
Data Index: 3345213 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0996. Min Act: -0.1698
Data Index: 1236918 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0996. Min Act: -0.1637
Data Index: 4901669 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.1164. Min Act: -0.1695
Data Index: 312455 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0829. Min Act: -0.1684
Data Index: 3754129 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0829. Min Act: -0.1700
Data Index: 3886286 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0829. Min Act: -0.1696
Data Index: 6725537 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0829. Min Act: -0.1417
Data Index: 2828700 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0661. Min Act: -0.1673
Data Index: 7769429 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1700
Data Index: 3454022 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1677
Data Index: 5053717 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1700
Data Index: 3667888 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1700
Data Index: 5830279 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1700
Data Index: 5302114 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1697
Data Index: 2570481 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1498. Min Range: -2.1498
Max Act: 2.0493. Min Act: -0.1698
Data Index: 4933050 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19