Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.9347. Min Act: -0.1700
Data Index: 4503713 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.8871. Min Act: -0.1700
Data Index: 2422217 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.8553. Min Act: -0.1700
Data Index: 5039394 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.8076. Min Act: -0.1700
Data Index: 1684600 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.8076. Min Act: -0.1700
Data Index: 99446 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7917. Min Act: -0.1700
Data Index: 8079380 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7758. Min Act: -0.1700
Data Index: 7914190 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7758. Min Act: -0.1700
Data Index: 1371927 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7758. Min Act: -0.1700
Data Index: 2167452 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7917. Min Act: -0.1700
Data Index: 3004817 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7598. Min Act: -0.1700
Data Index: 1087954 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7598. Min Act: -0.1700
Data Index: 8800806 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7598. Min Act: -0.1700
Data Index: 6000985 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7439. Min Act: -0.1700
Data Index: 949274 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7279. Min Act: -0.1700
Data Index: 5090963 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7439. Min Act: -0.1700
Data Index: 5427577 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7119. Min Act: -0.1700
Data Index: 4100766 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7119. Min Act: -0.1700
Data Index: 7464559 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7119. Min Act: -0.1700
Data Index: 7183238 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9347. Min Range: -2.9347
Max Act: 2.7119. Min Act: -0.1700
Data Index: 4573654 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19