Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.7120. Min Act: -0.1700
Data Index: 4119261 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.6495. Min Act: -0.1700
Data Index: 6777568 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.6495. Min Act: -0.1700
Data Index: 1619721 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.6495. Min Act: -0.1700
Data Index: 1470854 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.6495. Min Act: -0.1700
Data Index: 6777578 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.6495. Min Act: -0.1700
Data Index: 6777555 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5870. Min Act: -0.1700
Data Index: 1619724 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5870. Min Act: -0.1700
Data Index: 6777580 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5870. Min Act: -0.1700
Data Index: 2889393 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 2664174 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 3048194 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 6777557 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 2889397 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 1619719 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5870. Min Act: -0.1700
Data Index: 4119258 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 4119262 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 1619700 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.4620. Min Act: -0.1700
Data Index: 1619708 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.5245. Min Act: -0.1700
Data Index: 1619716 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7120. Min Range: -8.7120
Max Act: 8.4620. Min Act: -0.1700
Data Index: 3540004 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19