Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5437 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.6486. Min Act: -0.1700
Data Index: 4010223 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5549. Min Act: -0.1700
Data Index: 7677660 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5861. Min Act: -0.1700
Data Index: 1218497 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5861. Min Act: -0.1700
Data Index: 4753238 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5861. Min Act: -0.1700
Data Index: 7325553 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5861. Min Act: -0.1700
Data Index: 764058 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5861. Min Act: -0.1700
Data Index: 6788708 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5236. Min Act: -0.1700
Data Index: 4753086 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5236. Min Act: -0.1700
Data Index: 3258828 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5236. Min Act: -0.1700
Data Index: 8224152 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5236. Min Act: -0.1700
Data Index: 8762755 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.5236. Min Act: -0.1700
Data Index: 8630183 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 1864568 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 519045 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 8615591 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 8256539 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 2863630 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4924. Min Act: -0.1700
Data Index: 6457972 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3960549 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6486. Min Range: -4.6486
Max Act: 4.4611. Min Act: -0.1700
Data Index: 7478760 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19