Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.4178. Min Act: -0.1699
Data Index: 7990981 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.3650. Min Act: -0.1586
Data Index: 7990987 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.3297. Min Act: -0.1699
Data Index: 1908178 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2944. Min Act: -0.1692
Data Index: 7990985 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2944. Min Act: -0.1700
Data Index: 1071959 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2944. Min Act: -0.1699
Data Index: 55579 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2768. Min Act: -0.1700
Data Index: 5078032 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2768. Min Act: -0.1700
Data Index: 8038024 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2944. Min Act: -0.1698
Data Index: 2054807 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2768. Min Act: -0.1700
Data Index: 893593 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2591. Min Act: -0.1699
Data Index: 7606040 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2415. Min Act: -0.1681
Data Index: 8667959 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2415. Min Act: -0.1698
Data Index: 1594504 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2415. Min Act: -0.1700
Data Index: 7715886 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2415. Min Act: -0.1679
Data Index: 5559811 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2415. Min Act: -0.1700
Data Index: 7384872 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2239. Min Act: -0.1700
Data Index: 1094199 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2239. Min Act: -0.1699
Data Index: 6133939 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2239. Min Act: -0.1700
Data Index: 3778479 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4178. Min Range: -1.4178
Max Act: 1.2239. Min Act: -0.1700
Data Index: 1028071 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19