Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3132 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.9959. Min Act: -0.1669
Data Index: 3928694 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7910. Min Act: -0.1697
Data Index: 8366634 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7910. Min Act: -0.1700
Data Index: 2033702 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7743. Min Act: -0.1698
Data Index: 284266 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7660. Min Act: -0.1700
Data Index: 5848124 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7329. Min Act: -0.1698
Data Index: 5171772 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7246. Min Act: -0.1695
Data Index: 6670787 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.7082. Min Act: -0.1700
Data Index: 4094222 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6919. Min Act: -0.1700
Data Index: 284289 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6919. Min Act: -0.1695
Data Index: 724845 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6919. Min Act: -0.1700
Data Index: 1153151 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6919. Min Act: -0.1700
Data Index: 4167008 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6838. Min Act: -0.1670
Data Index: 6155118 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6838. Min Act: -0.1700
Data Index: 7471701 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6676. Min Act: -0.1694
Data Index: 4835319 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6676. Min Act: -0.1700
Data Index: 4094221 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6515. Min Act: -0.1698
Data Index: 2678695 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6515. Min Act: -0.1700
Data Index: 4813640 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6515. Min Act: -0.1698
Data Index: 1741313 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9959. Min Range: -0.9959
Max Act: 0.6435. Min Act: -0.1676
Data Index: 854283 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19