Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5628 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5181. Min Range: -6.5181
Max Act: 6.5181. Min Act: -0.1700
Data Index: 5296437 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5181. Min Range: -6.5181
Max Act: 6.2681. Min Act: -0.1700
Data Index: 2515056 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5181. Min Range: -6.5181
Max Act: 6.0493. Min Act: -0.1700
Data Index: 7455514 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5181. Min Range: -6.5181
Max Act: 6.0181. Min Act: -0.1700
Data Index: 4346416 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.9556. Min Act: -0.1700
Data Index: 7148709 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.9243. Min Act: -0.1700
Data Index: 3146818 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3111532 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.8618. Min Act: -0.1700
Data Index: 382170 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.8306. Min Act: -0.1700
Data Index: 1422711 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.8306. Min Act: -0.1700
Data Index: 4346417 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.7681. Min Act: -0.1700
Data Index: 1958773 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.7368. Min Act: -0.1700
Data Index: 602396 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.7368. Min Act: -0.1700
Data Index: 4999648 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.7368. Min Act: -0.1700
Data Index: 7329057 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 3720168 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 7141233 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 7232798 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 1585806 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 2011536 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5181. Min Range: -6.5181
Max Act: 5.6743. Min Act: -0.1700
Data Index: 3720161 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19