Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.9827. Min Act: -0.1700
Data Index: 1470581 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.9202. Min Act: -0.1700
Data Index: 1731069 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.7952. Min Act: -0.1700
Data Index: 4305839 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.7327. Min Act: -0.1700
Data Index: 8467241 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.7327. Min Act: -0.1700
Data Index: 356241 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.6702. Min Act: -0.1700
Data Index: 8386663 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.6077. Min Act: -0.1700
Data Index: 2451550 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.5452. Min Act: -0.1700
Data Index: 5366028 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4827. Min Act: -0.1700
Data Index: 6478436 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4827. Min Act: -0.1700
Data Index: 6856823 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.5139. Min Act: -0.1700
Data Index: 5405451 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4202. Min Act: -0.1700
Data Index: 3051953 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4202. Min Act: -0.1700
Data Index: 6484923 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4202. Min Act: -0.1700
Data Index: 3037235 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.4202. Min Act: -0.1700
Data Index: 1138804 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 4568000 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 7066533 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3889. Min Act: -0.1700
Data Index: 7500922 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3577. Min Act: -0.1700
Data Index: 5933235 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9827. Min Range: -7.9827
Max Act: 7.3577. Min Act: -0.1700
Data Index: 800386 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19