Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.2800. Min Act: -0.1700
Data Index: 825239 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.2271. Min Act: -0.1700
Data Index: 6269745 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.2271. Min Act: -0.1700
Data Index: 420286 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1743. Min Act: -0.1700
Data Index: 3302590 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1743. Min Act: -0.1700
Data Index: 1854397 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1215. Min Act: -0.1700
Data Index: 7874866 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1215. Min Act: -0.1700
Data Index: 5473407 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1215. Min Act: -0.1700
Data Index: 4826015 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.1040. Min Act: -0.1700
Data Index: 6763032 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0865. Min Act: -0.1700
Data Index: 8433362 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0690. Min Act: -0.1700
Data Index: 2648056 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0690. Min Act: -0.1700
Data Index: 4603166 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0690. Min Act: -0.1700
Data Index: 2919025 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 5185832 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 6647 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 1826663 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 3691286 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 4357108 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 877499 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2800. Min Range: -1.2800
Max Act: 1.0515. Min Act: -0.1700
Data Index: 2782220 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19