Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0364. Min Range: -4.0364
Max Act: 4.0364. Min Act: -0.1700
Data Index: 2212343 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0364. Min Range: -4.0364
Max Act: 4.0051. Min Act: -0.1700
Data Index: 5576283 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0364. Min Range: -4.0364
Max Act: 4.0051. Min Act: -0.1700
Data Index: 2731356 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.8801. Min Act: -0.1700
Data Index: 1716079 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.8175. Min Act: -0.1700
Data Index: 5576290 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7863. Min Act: -0.1700
Data Index: 946297 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 7422227 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 7068084 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 5757032 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 6782384 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7237. Min Act: -0.1700
Data Index: 7518944 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 78319 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7550. Min Act: -0.1700
Data Index: 8197593 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.7237. Min Act: -0.1700
Data Index: 6141052 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6611. Min Act: -0.1700
Data Index: 8397022 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6924. Min Act: -0.1700
Data Index: 747314 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6611. Min Act: -0.1700
Data Index: 3910118 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6455. Min Act: -0.1700
Data Index: 6682772 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6455. Min Act: -0.1700
Data Index: 27650 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0364. Min Range: -4.0364
Max Act: 3.6298. Min Act: -0.1700
Data Index: 493497 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19