Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2155. Min Range: -5.2155
Max Act: 5.2155. Min Act: -0.1700
Data Index: 8057275 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2155. Min Range: -5.2155
Max Act: 5.0905. Min Act: -0.1700
Data Index: 1142475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2155. Min Range: -5.2155
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7067795 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2155. Min Range: -5.2155
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3489500 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2155. Min Range: -5.2155
Max Act: 5.0280. Min Act: -0.1700
Data Index: 3352607 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.9343. Min Act: -0.1700
Data Index: 2395079 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.9030. Min Act: -0.1700
Data Index: 5920341 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.9030. Min Act: -0.1700
Data Index: 3845468 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8718. Min Act: -0.1700
Data Index: 8049901 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8093. Min Act: -0.1700
Data Index: 2527214 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3408892 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8405. Min Act: -0.1700
Data Index: 2894564 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8405. Min Act: -0.1700
Data Index: 6010196 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7780. Min Act: -0.1700
Data Index: 477629 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.8093. Min Act: -0.1700
Data Index: 4443357 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7780. Min Act: -0.1700
Data Index: 6640168 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7780. Min Act: -0.1700
Data Index: 6523470 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7468. Min Act: -0.1700
Data Index: 492745 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7780. Min Act: -0.1700
Data Index: 619713 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2155. Min Range: -5.2155
Max Act: 4.7468. Min Act: -0.1700
Data Index: 7774921 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19