Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5144 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.9606. Min Act: -0.1700
Data Index: 8026561 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.8668. Min Act: -0.1700
Data Index: 970728 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.8356. Min Act: -0.1700
Data Index: 5831932 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.8356. Min Act: -0.1700
Data Index: 8658431 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.7418. Min Act: -0.1700
Data Index: 8644971 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.7106. Min Act: -0.1700
Data Index: 6621708 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1056388 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.6168. Min Act: -0.1700
Data Index: 7130696 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.6168. Min Act: -0.1700
Data Index: 6912726 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.6168. Min Act: -0.1700
Data Index: 3121423 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.4918. Min Act: -0.1700
Data Index: 5081194 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.4606. Min Act: -0.1700
Data Index: 4756138 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.4293. Min Act: -0.1700
Data Index: 5630983 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.4293. Min Act: -0.1700
Data Index: 128119 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.3668. Min Act: -0.1700
Data Index: 2067206 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.3668. Min Act: -0.1700
Data Index: 7454853 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.3043. Min Act: -0.1700
Data Index: 6202733 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.2731. Min Act: -0.1700
Data Index: 960195 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.2731. Min Act: -0.1700
Data Index: 7284049 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9606. Min Range: -5.9606
Max Act: 5.2731. Min Act: -0.1700
Data Index: 3950804 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19