Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1406269 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.4487. Min Act: -0.1700
Data Index: 2118907 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.3862. Min Act: -0.1700
Data Index: 5877122 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.2925. Min Act: -0.1700
Data Index: 1010633 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.2300. Min Act: -0.1700
Data Index: 8372590 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.2300. Min Act: -0.1700
Data Index: 2890684 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1675. Min Act: -0.1700
Data Index: 1397238 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1675. Min Act: -0.1700
Data Index: 614041 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1675. Min Act: -0.1700
Data Index: 4199169 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1050. Min Act: -0.1700
Data Index: 3840905 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1050. Min Act: -0.1700
Data Index: 1516016 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1050. Min Act: -0.1700
Data Index: 5440814 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6873961 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0737. Min Act: -0.1700
Data Index: 7153535 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0737. Min Act: -0.1700
Data Index: 4112632 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0737. Min Act: -0.1700
Data Index: 5751284 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0425. Min Act: -0.1700
Data Index: 1476545 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0737. Min Act: -0.1700
Data Index: 3682054 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0425. Min Act: -0.1700
Data Index: 8291382 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9800. Min Act: -0.1700
Data Index: 5967449 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19