Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2020. Min Range: -7.2020
Max Act: 7.2020. Min Act: -0.1700
Data Index: 7171060 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.9208. Min Act: -0.1700
Data Index: 8490395 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.9208. Min Act: -0.1700
Data Index: 7801528 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.9208. Min Act: -0.1700
Data Index: 1702767 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.9208. Min Act: -0.1700
Data Index: 7153018 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8895. Min Act: -0.1700
Data Index: 3673653 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7958. Min Act: -0.1700
Data Index: 759813 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8270. Min Act: -0.1700
Data Index: 2971617 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8583. Min Act: -0.1700
Data Index: 597982 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8270. Min Act: -0.1700
Data Index: 1826825 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7958. Min Act: -0.1700
Data Index: 4200459 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8270. Min Act: -0.1700
Data Index: 4532800 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.8270. Min Act: -0.1700
Data Index: 3979414 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7645. Min Act: -0.1700
Data Index: 3374608 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7333. Min Act: -0.1700
Data Index: 7732917 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7333. Min Act: -0.1700
Data Index: 1129470 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7333. Min Act: -0.1700
Data Index: 3269839 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7020. Min Act: -0.1700
Data Index: 4653546 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7020. Min Act: -0.1700
Data Index: 798625 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2020. Min Range: -7.2020
Max Act: 6.7020. Min Act: -0.1700
Data Index: 927930 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19