Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5740 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4465. Min Act: -0.1700
Data Index: 3424385 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4465. Min Act: -0.1700
Data Index: 5463606 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4152. Min Act: -0.1700
Data Index: 1157912 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4152. Min Act: -0.1700
Data Index: 7417233 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3995. Min Act: -0.1700
Data Index: 527405 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3525. Min Act: -0.1700
Data Index: 6870173 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3681. Min Act: -0.1700
Data Index: 8509218 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 3068791 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3525. Min Act: -0.1700
Data Index: 1673996 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3211. Min Act: -0.1700
Data Index: 3562050 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3054. Min Act: -0.1700
Data Index: 7604782 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2897. Min Act: -0.1700
Data Index: 6786779 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2740. Min Act: -0.1700
Data Index: 598697 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2583. Min Act: -0.1700
Data Index: 1404824 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2740. Min Act: -0.1700
Data Index: 5050227 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2583. Min Act: -0.1700
Data Index: 770115 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2583. Min Act: -0.1700
Data Index: 3941139 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2426. Min Act: -0.1700
Data Index: 2452030 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2583. Min Act: -0.1700
Data Index: 702266 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.2268. Min Act: -0.1700
Data Index: 5896730 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19