Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.6050. Min Act: -0.1700
Data Index: 8771713 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5738. Min Act: -0.1700
Data Index: 4197698 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.5425. Min Act: -0.1700
Data Index: 6239436 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 7932930 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 513900 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 7247594 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4800. Min Act: -0.1700
Data Index: 2645413 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 2726081 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3863. Min Act: -0.1700
Data Index: 340264 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3550. Min Act: -0.1700
Data Index: 879622 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4573673 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3550. Min Act: -0.1700
Data Index: 5864900 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3550. Min Act: -0.1700
Data Index: 3810833 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3238. Min Act: -0.1700
Data Index: 8122893 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3238. Min Act: -0.1700
Data Index: 3992780 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3238. Min Act: -0.1700
Data Index: 372541 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3238. Min Act: -0.1700
Data Index: 1860914 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.3238. Min Act: -0.1700
Data Index: 6795881 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.2925. Min Act: -0.1700
Data Index: 1879236 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6050. Min Range: -5.6050
Max Act: 5.2925. Min Act: -0.1700
Data Index: 5880061 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19