Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.7444. Min Act: -0.1700
Data Index: 3298165 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.7131. Min Act: -0.1700
Data Index: 4733076 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.6194. Min Act: -0.1700
Data Index: 6870461 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.5569. Min Act: -0.1700
Data Index: 3053724 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.5256. Min Act: -0.1700
Data Index: 2796052 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.5256. Min Act: -0.1700
Data Index: 1809299 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4944. Min Act: -0.1700
Data Index: 3688469 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4631. Min Act: -0.1700
Data Index: 892134 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4944. Min Act: -0.1700
Data Index: 976512 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.5256. Min Act: -0.1700
Data Index: 4966921 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4319. Min Act: -0.1700
Data Index: 7999066 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4631. Min Act: -0.1700
Data Index: 8307245 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4319. Min Act: -0.1700
Data Index: 4482670 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4631. Min Act: -0.1700
Data Index: 880477 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3730566 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4944. Min Act: -0.1700
Data Index: 2593955 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4631. Min Act: -0.1700
Data Index: 5938870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4006. Min Act: -0.1700
Data Index: 2858293 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.4006. Min Act: -0.1700
Data Index: 5969905 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7444. Min Range: -5.7444
Max Act: 5.3694. Min Act: -0.1700
Data Index: 4858222 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19