Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1938 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.5461. Min Act: -0.1700
Data Index: 1735685 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.5149. Min Act: -0.1700
Data Index: 316515 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.2336. Min Act: -0.1700
Data Index: 495933 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.2649. Min Act: -0.1700
Data Index: 1735682 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.2024. Min Act: -0.1700
Data Index: 1735683 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.1086. Min Act: -0.1700
Data Index: 4012906 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.1399. Min Act: -0.1700
Data Index: 495934 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.1086. Min Act: -0.1700
Data Index: 8621885 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0774. Min Act: -0.1700
Data Index: 1735681 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0774. Min Act: -0.1700
Data Index: 1108765 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0774. Min Act: -0.1700
Data Index: 1499044 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0774. Min Act: -0.1700
Data Index: 1735687 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0461. Min Act: -0.1700
Data Index: 565663 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0461. Min Act: -0.1700
Data Index: 886803 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0149. Min Act: -0.1700
Data Index: 5275037 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0461. Min Act: -0.1700
Data Index: 5275038 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5461. Min Range: -6.5461
Max Act: 6.0149. Min Act: -0.1700
Data Index: 565659 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5461. Min Range: -6.5461
Max Act: 5.9836. Min Act: -0.1700
Data Index: 2987799 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5461. Min Range: -6.5461
Max Act: 5.9836. Min Act: -0.1700
Data Index: 376854 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5461. Min Range: -6.5461
Max Act: 5.9524. Min Act: -0.1700
Data Index: 495932 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19