Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.9189. Min Act: -0.1700
Data Index: 4429831 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.7001. Min Act: -0.1700
Data Index: 200432 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5933853 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.6376. Min Act: -0.1700
Data Index: 4884893 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.5126. Min Act: -0.1700
Data Index: 4186824 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.5126. Min Act: -0.1700
Data Index: 6427174 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.4501. Min Act: -0.1700
Data Index: 8571240 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.4501. Min Act: -0.1700
Data Index: 4602234 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.4189. Min Act: -0.1700
Data Index: 6630008 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.4189. Min Act: -0.1700
Data Index: 5774298 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3564. Min Act: -0.1700
Data Index: 153999 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3876. Min Act: -0.1700
Data Index: 6539647 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3564. Min Act: -0.1700
Data Index: 8494868 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3564. Min Act: -0.1700
Data Index: 6650898 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3564. Min Act: -0.1700
Data Index: 4133358 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3564. Min Act: -0.1700
Data Index: 5158780 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.3251. Min Act: -0.1700
Data Index: 5767278 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.2939. Min Act: -0.1700
Data Index: 1187093 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.2939. Min Act: -0.1700
Data Index: 4050435 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9189. Min Range: -5.9189
Max Act: 5.2626. Min Act: -0.1700
Data Index: 1413862 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19