Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.9836. Min Act: -0.1700
Data Index: 8339993 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8898. Min Act: -0.1700
Data Index: 6043454 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5121588 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8586. Min Act: -0.1700
Data Index: 61478 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8273. Min Act: -0.1700
Data Index: 2989178 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8273. Min Act: -0.1700
Data Index: 117346 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.8273. Min Act: -0.1700
Data Index: 8251648 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7336. Min Act: -0.1700
Data Index: 2372195 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7648. Min Act: -0.1700
Data Index: 3891586 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7336. Min Act: -0.1700
Data Index: 5064554 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7961. Min Act: -0.1700
Data Index: 7488500 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7648. Min Act: -0.1700
Data Index: 2647089 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7648. Min Act: -0.1700
Data Index: 5478534 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7336. Min Act: -0.1700
Data Index: 2163982 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7336. Min Act: -0.1700
Data Index: 4383453 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7023. Min Act: -0.1700
Data Index: 2796585 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.7023. Min Act: -0.1700
Data Index: 5098103 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.6711. Min Act: -0.1700
Data Index: 2216571 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.6711. Min Act: -0.1700
Data Index: 1776830 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9836. Min Range: -4.9836
Max Act: 4.6711. Min Act: -0.1700
Data Index: 1494009 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19