Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 111 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2407. Min Range: -6.2407
Max Act: 6.2407. Min Act: -0.1700
Data Index: 1655040 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2407. Min Range: -6.2407
Max Act: 6.0845. Min Act: -0.1700
Data Index: 2615967 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2407. Min Range: -6.2407
Max Act: 6.0845. Min Act: -0.1700
Data Index: 7485042 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2407. Min Range: -6.2407
Max Act: 6.0532. Min Act: -0.1700
Data Index: 3825412 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2407. Min Range: -6.2407
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3163052 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.9595. Min Act: -0.1700
Data Index: 2647530 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.9595. Min Act: -0.1700
Data Index: 8610651 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.9595. Min Act: -0.1700
Data Index: 2012770 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8970. Min Act: -0.1700
Data Index: 3626496 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 7396351 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2776549 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 413430 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2713063 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 1661486 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8657. Min Act: -0.1700
Data Index: 6711975 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8345. Min Act: -0.1700
Data Index: 4229621 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8345. Min Act: -0.1700
Data Index: 8076455 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8345. Min Act: -0.1700
Data Index: 2519572 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8032. Min Act: -0.1700
Data Index: 6997052 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2407. Min Range: -6.2407
Max Act: 5.8032. Min Act: -0.1700
Data Index: 1223920 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19