Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.2131. Min Range: -14.2131
Max Act: 14.2131. Min Act: -0.1700
Data Index: 4617358 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2131. Min Range: -14.2131
Max Act: 14.1506. Min Act: -0.1698
Data Index: 5399249 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.9631. Min Act: -0.1700
Data Index: 360050 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.9631. Min Act: -0.1700
Data Index: 2807451 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.9631. Min Act: -0.1698
Data Index: 4372936 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.7756. Min Act: -0.1700
Data Index: 1977679 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.5256. Min Act: -0.1700
Data Index: 1860159 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2756. Min Act: -0.1700
Data Index: 5008461 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.4006. Min Act: -0.1700
Data Index: 4047783 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.3381. Min Act: -0.1700
Data Index: 7318829 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.3381. Min Act: -0.1700
Data Index: 315365 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2756. Min Act: -0.1700
Data Index: 5130157 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2131. Min Act: -0.1700
Data Index: 8532341 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2756. Min Act: -0.1700
Data Index: 2451476 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2131. Min Act: -0.1700
Data Index: 4091689 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2131. Min Act: -0.1700
Data Index: 102512 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.2131. Min Act: -0.1700
Data Index: 3940386 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.0881. Min Act: -0.1700
Data Index: 7829423 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.1506. Min Act: -0.1700
Data Index: 473282 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2131. Min Range: -14.2131
Max Act: 13.1506. Min Act: -0.1700
Data Index: 6191340 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19