Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.9282. Min Act: -0.1700
Data Index: 8712568 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.5532. Min Act: -0.1700
Data Index: 6706825 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.5220. Min Act: -0.1700
Data Index: 4691704 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.5220. Min Act: -0.1700
Data Index: 1945599 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.4282. Min Act: -0.1700
Data Index: 6454132 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.4595. Min Act: -0.1700
Data Index: 7903320 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.3970. Min Act: -0.1700
Data Index: 8813242 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.3657. Min Act: -0.1700
Data Index: 708354 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.3345. Min Act: -0.1700
Data Index: 3646948 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2720. Min Act: -0.1700
Data Index: 1279091 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2407. Min Act: -0.1700
Data Index: 3881772 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.3032. Min Act: -0.1700
Data Index: 5448007 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2407. Min Act: -0.1700
Data Index: 1707504 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2407. Min Act: -0.1700
Data Index: 7903612 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2407. Min Act: -0.1700
Data Index: 6861576 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2095. Min Act: -0.1700
Data Index: 8479987 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2095. Min Act: -0.1700
Data Index: 4285945 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2095. Min Act: -0.1700
Data Index: 1733317 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.2095. Min Act: -0.1700
Data Index: 158970 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9282. Min Range: -4.9282
Max Act: 4.1782. Min Act: -0.1700
Data Index: 480050 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19