Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.7550. Min Act: -0.1700
Data Index: 2380516 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.6925. Min Act: -0.1700
Data Index: 5059948 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.6613. Min Act: -0.1700
Data Index: 1538713 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1269021 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5988. Min Act: -0.1700
Data Index: 2911696 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4549025 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5650003 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5675. Min Act: -0.1700
Data Index: 7856384 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5363. Min Act: -0.1700
Data Index: 1480283 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5675. Min Act: -0.1700
Data Index: 7243601 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6759808 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5675. Min Act: -0.1700
Data Index: 3671147 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5363. Min Act: -0.1700
Data Index: 2320064 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5363. Min Act: -0.1700
Data Index: 8355656 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5286106 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4738. Min Act: -0.1700
Data Index: 1630914 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5050. Min Act: -0.1700
Data Index: 6321259 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4425. Min Act: -0.1700
Data Index: 7822929 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4738. Min Act: -0.1700
Data Index: 7308372 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4738. Min Act: -0.1700
Data Index: 2365027 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19