Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.3901. Min Act: -0.1700
Data Index: 4414442 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.3589. Min Act: -0.1700
Data Index: 732196 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.3589. Min Act: -0.1700
Data Index: 6747700 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2964. Min Act: -0.1700
Data Index: 5297490 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 4413344 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 7880098 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 3527701 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2339. Min Act: -0.1700
Data Index: 512452 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1713. Min Act: -0.1700
Data Index: 2122272 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1713. Min Act: -0.1700
Data Index: 3997484 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2026. Min Act: -0.1700
Data Index: 7388884 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1713. Min Act: -0.1700
Data Index: 2189270 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1713. Min Act: -0.1700
Data Index: 7673722 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1401. Min Act: -0.1700
Data Index: 5627824 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1713. Min Act: -0.1700
Data Index: 5158369 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1088. Min Act: -0.1700
Data Index: 6788532 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1088. Min Act: -0.1700
Data Index: 4137749 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1088. Min Act: -0.1700
Data Index: 3136703 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1401. Min Act: -0.1700
Data Index: 4851343 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.1088. Min Act: -0.1700
Data Index: 2738303 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19