Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4391 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.8597. Min Act: -0.1700
Data Index: 8657042 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.7659. Min Act: -0.1700
Data Index: 651726 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.6409. Min Act: -0.1700
Data Index: 4505629 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.6409. Min Act: -0.1700
Data Index: 3451566 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.6409. Min Act: -0.1700
Data Index: 3465760 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.6409. Min Act: -0.1700
Data Index: 1202977 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5784. Min Act: -0.1700
Data Index: 8681262 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5784. Min Act: -0.1700
Data Index: 1826892 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5472. Min Act: -0.1700
Data Index: 669504 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5472. Min Act: -0.1700
Data Index: 3332927 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5159. Min Act: -0.1700
Data Index: 8650324 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5159. Min Act: -0.1700
Data Index: 5446247 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.5159. Min Act: -0.1700
Data Index: 4851821 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4847. Min Act: -0.1700
Data Index: 1768964 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4847. Min Act: -0.1700
Data Index: 3554947 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4534. Min Act: -0.1700
Data Index: 3776529 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4534. Min Act: -0.1700
Data Index: 3862651 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4534. Min Act: -0.1700
Data Index: 4048930 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4222. Min Act: -0.1700
Data Index: 450297 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8597. Min Range: -6.8597
Max Act: 6.4222. Min Act: -0.1700
Data Index: 7880044 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19