Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 560 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.6684. Min Act: -0.1700
Data Index: 8806356 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.6527. Min Act: -0.1700
Data Index: 5203840 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.6058. Min Act: -0.1700
Data Index: 2445229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.5745. Min Act: -0.1700
Data Index: 6860369 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.5432. Min Act: -0.1700
Data Index: 2856795 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.5275. Min Act: -0.1700
Data Index: 6759878 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.4022. Min Act: -0.1700
Data Index: 1421491 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.4179. Min Act: -0.1700
Data Index: 3661305 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3865. Min Act: -0.1700
Data Index: 579741 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 5369799 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 1327945 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 2683478 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 4652872 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3394. Min Act: -0.1700
Data Index: 4138158 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3551. Min Act: -0.1700
Data Index: 6212864 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 2816391 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3708. Min Act: -0.1700
Data Index: 5100606 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3551. Min Act: -0.1700
Data Index: 7653723 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3865. Min Act: -0.1700
Data Index: 5305016 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6684. Min Range: -3.6684
Max Act: 3.3394. Min Act: -0.1700
Data Index: 726871 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19