Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0193. Min Range: -6.0193
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2908201 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.8631. Min Act: -0.1700
Data Index: 4504077 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1283646 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.7693. Min Act: -0.1700
Data Index: 771746 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.6756. Min Act: -0.1700
Data Index: 6028553 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5299963 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.6443. Min Act: -0.1700
Data Index: 8228167 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.6131. Min Act: -0.1700
Data Index: 1225126 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7286394 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.5818. Min Act: -0.1700
Data Index: 895377 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.5506. Min Act: -0.1700
Data Index: 1172889 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.5506. Min Act: -0.1700
Data Index: 6258120 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.5506. Min Act: -0.1700
Data Index: 1856137 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4881. Min Act: -0.1700
Data Index: 4530151 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4568. Min Act: -0.1700
Data Index: 3768372 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4568. Min Act: -0.1700
Data Index: 8721401 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4568. Min Act: -0.1700
Data Index: 4838134 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4256. Min Act: -0.1700
Data Index: 2797347 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1795427 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0193. Min Range: -6.0193
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1607967 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19