Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.8509. Min Act: -0.1697
Data Index: 4483514 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.8509. Min Act: -0.1700
Data Index: 3716264 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.8337. Min Act: -0.1700
Data Index: 1284410 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.8251. Min Act: -0.1699
Data Index: 1973492 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7735. Min Act: -0.1700
Data Index: 1448412 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7735. Min Act: -0.1700
Data Index: 5943282 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7649. Min Act: -0.1700
Data Index: 4524607 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7649. Min Act: -0.1700
Data Index: 4626942 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7563. Min Act: -0.1699
Data Index: 7904272 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7390. Min Act: -0.1700
Data Index: 65424 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7217. Min Act: -0.1700
Data Index: 1623703 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7044. Min Act: -0.1700
Data Index: 4769878 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7130. Min Act: -0.1700
Data Index: 2737068 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7130. Min Act: -0.1700
Data Index: 4124553 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7130. Min Act: -0.1700
Data Index: 8248407 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7044. Min Act: -0.1700
Data Index: 2100748 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.6957. Min Act: -0.1700
Data Index: 822334 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.6957. Min Act: -0.1697
Data Index: 2603763 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.6957. Min Act: -0.1699
Data Index: 5061983 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8509. Min Range: -1.8509
Max Act: 1.7044. Min Act: -0.1699
Data Index: 5019821 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19