Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.6493. Min Act: -0.1700
Data Index: 7226519 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.5243. Min Act: -0.1700
Data Index: 1478379 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.4618. Min Act: -0.1700
Data Index: 6645477 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3681. Min Act: -0.1700
Data Index: 8601029 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3368. Min Act: -0.1700
Data Index: 4469010 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2743. Min Act: -0.1700
Data Index: 5844558 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2743. Min Act: -0.1700
Data Index: 225745 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2118. Min Act: -0.1700
Data Index: 4957198 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2431. Min Act: -0.1700
Data Index: 286569 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2431. Min Act: -0.1700
Data Index: 5644178 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1806. Min Act: -0.1700
Data Index: 5362587 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1806. Min Act: -0.1700
Data Index: 4957206 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1493. Min Act: -0.1700
Data Index: 3748589 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1806. Min Act: -0.1700
Data Index: 7925806 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1806. Min Act: -0.1700
Data Index: 272634 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1493. Min Act: -0.1700
Data Index: 6983366 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1493. Min Act: -0.1700
Data Index: 2590410 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1181. Min Act: -0.1700
Data Index: 4779447 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.1181. Min Act: -0.1700
Data Index: 4500398 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.0868. Min Act: -0.1700
Data Index: 2623163 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19