Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1337 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2080. Min Range: -7.2080
Max Act: 5.4736. Min Act: -0.1700
Data Index: 1280783 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.9893. Min Act: -0.1699
Data Index: 5881917 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2080. Min Range: -7.2080
Max Act: 7.1768. Min Act: -0.1700
Data Index: 3764985 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2080. Min Range: -7.2080
Max Act: 7.1143. Min Act: -0.1700
Data Index: 5649389 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2080. Min Range: -7.2080
Max Act: 7.2080. Min Act: -0.1700
Data Index: 835561 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.8643. Min Act: -0.1700
Data Index: 6150464 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.8018. Min Act: -0.1700
Data Index: 6150474 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.8330. Min Act: -0.1700
Data Index: 5289145 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.5205. Min Act: -0.1700
Data Index: 3310901 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.7705. Min Act: -0.1700
Data Index: 7278853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.7705. Min Act: -0.1700
Data Index: 385360 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.7705. Min Act: -0.1700
Data Index: 4807558 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.7393. Min Act: -0.1700
Data Index: 7572909 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.7393. Min Act: -0.1700
Data Index: 7922497 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.6768. Min Act: -0.1700
Data Index: 8115945 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.6768. Min Act: -0.1700
Data Index: 188055 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.6455. Min Act: -0.1700
Data Index: 8711453 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.8643. Min Act: -0.1700
Data Index: 2073673 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.6143. Min Act: -0.1700
Data Index: 846006 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2080. Min Range: -7.2080
Max Act: 6.6455. Min Act: -0.1700
Data Index: 135747 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19