Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8648. Min Range: -7.8648
Max Act: 7.8648. Min Act: -0.1700
Data Index: 1118058 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8648. Min Range: -7.8648
Max Act: 7.4273. Min Act: -0.1698
Data Index: 1968425 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8648. Min Range: -7.8648
Max Act: 7.2398. Min Act: -0.1700
Data Index: 3214618 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.9273. Min Act: -0.1699
Data Index: 5274186 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.9586. Min Act: -0.1700
Data Index: 4621828 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.9273. Min Act: -0.1693
Data Index: 1133061 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.8961. Min Act: -0.1697
Data Index: 7298245 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.8336. Min Act: -0.1700
Data Index: 4298113 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.8023. Min Act: -0.1700
Data Index: 5202230 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7711. Min Act: -0.1700
Data Index: 5123332 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7398. Min Act: -0.1700
Data Index: 3295171 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7711. Min Act: -0.1700
Data Index: 5812150 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7711. Min Act: -0.1700
Data Index: 1681776 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.8336. Min Act: -0.1700
Data Index: 1748767 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7711. Min Act: -0.1700
Data Index: 5471732 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.6148. Min Act: -0.1699
Data Index: 8006637 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7086. Min Act: -0.1700
Data Index: 839562 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7711. Min Act: -0.1699
Data Index: 6907889 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.7398. Min Act: -0.1698
Data Index: 2486670 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8648. Min Range: -7.8648
Max Act: 6.6773. Min Act: -0.1700
Data Index: 3616372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19