Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 600 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.7869. Min Act: -0.1700
Data Index: 2125363 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.6306. Min Act: -0.1700
Data Index: 391031 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.5994. Min Act: -0.1700
Data Index: 5249795 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4744. Min Act: -0.1700
Data Index: 5188656 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4584935 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4431. Min Act: -0.1700
Data Index: 7582457 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4119. Min Act: -0.1700
Data Index: 5134494 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4119. Min Act: -0.1700
Data Index: 6111206 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.4119. Min Act: -0.1700
Data Index: 8147691 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3806. Min Act: -0.1700
Data Index: 2197881 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3494. Min Act: -0.1700
Data Index: 812120 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3181. Min Act: -0.1700
Data Index: 2838076 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3181. Min Act: -0.1700
Data Index: 8269815 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3181. Min Act: -0.1700
Data Index: 4494068 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.3181. Min Act: -0.1700
Data Index: 7261314 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.2869. Min Act: -0.1700
Data Index: 2644376 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.2869. Min Act: -0.1700
Data Index: 3487424 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5875208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.2556. Min Act: -0.1700
Data Index: 7056606 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7869. Min Range: -6.7869
Max Act: 6.2556. Min Act: -0.1700
Data Index: 7887368 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19