Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.6490. Min Act: -0.1700
Data Index: 5458850 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.5865. Min Act: -0.1700
Data Index: 2226275 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.5865. Min Act: -0.1700
Data Index: 1355480 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.5552. Min Act: -0.1700
Data Index: 3441066 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.4302. Min Act: -0.1700
Data Index: 1924965 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3990. Min Act: -0.1700
Data Index: 6993901 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3990. Min Act: -0.1700
Data Index: 2030629 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1769085 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1809510 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3365. Min Act: -0.1700
Data Index: 4906600 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3365. Min Act: -0.1700
Data Index: 5463911 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3052. Min Act: -0.1700
Data Index: 1429714 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.3052. Min Act: -0.1700
Data Index: 3738229 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2427. Min Act: -0.1700
Data Index: 5991728 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2740. Min Act: -0.1700
Data Index: 3962956 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2740. Min Act: -0.1700
Data Index: 5184680 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2740. Min Act: -0.1700
Data Index: 8715596 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2427. Min Act: -0.1700
Data Index: 5780892 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2115. Min Act: -0.1700
Data Index: 1036370 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6490. Min Range: -6.6490
Max Act: 6.2115. Min Act: -0.1700
Data Index: 2067472 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19