Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0278. Min Range: -6.0278
Max Act: 6.0278. Min Act: -0.1700
Data Index: 675191 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.9653. Min Act: -0.1700
Data Index: 96594 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.8715. Min Act: -0.1700
Data Index: 6817705 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7162359 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7465. Min Act: -0.1700
Data Index: 3380726 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7465. Min Act: -0.1700
Data Index: 817668 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7153. Min Act: -0.1700
Data Index: 7126206 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7153. Min Act: -0.1700
Data Index: 3353685 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7153. Min Act: -0.1700
Data Index: 530690 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6840. Min Act: -0.1700
Data Index: 2431565 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7465. Min Act: -0.1700
Data Index: 8164995 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.7153. Min Act: -0.1700
Data Index: 5560763 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6840. Min Act: -0.1700
Data Index: 4039653 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6528. Min Act: -0.1700
Data Index: 1488716 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6528. Min Act: -0.1700
Data Index: 4011345 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6840. Min Act: -0.1700
Data Index: 1030647 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6528. Min Act: -0.1700
Data Index: 5487036 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6215. Min Act: -0.1700
Data Index: 1795873 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6528. Min Act: -0.1700
Data Index: 4038851 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0278. Min Range: -6.0278
Max Act: 5.6215. Min Act: -0.1700
Data Index: 56995 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19