Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0201. Min Range: -5.0201
Max Act: 5.0201. Min Act: -0.1700
Data Index: 6209622 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.9264. Min Act: -0.1700
Data Index: 2179221 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.9576. Min Act: -0.1700
Data Index: 7089202 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.9264. Min Act: -0.1700
Data Index: 745081 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.8326. Min Act: -0.1700
Data Index: 669340 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.8326. Min Act: -0.1700
Data Index: 447759 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.7389. Min Act: -0.1700
Data Index: 3821350 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6764. Min Act: -0.1700
Data Index: 1876897 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.7076. Min Act: -0.1700
Data Index: 7051948 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.7076. Min Act: -0.1700
Data Index: 3266196 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.7076. Min Act: -0.1700
Data Index: 8002599 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6764. Min Act: -0.1700
Data Index: 8246556 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6764. Min Act: -0.1700
Data Index: 4607387 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3438349 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6764. Min Act: -0.1700
Data Index: 122051 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6139. Min Act: -0.1700
Data Index: 8579410 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.5826. Min Act: -0.1700
Data Index: 7422884 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6139. Min Act: -0.1700
Data Index: 7963553 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.5826. Min Act: -0.1700
Data Index: 575697 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0201. Min Range: -5.0201
Max Act: 4.6451. Min Act: -0.1700
Data Index: 4916007 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19