Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0989. Min Range: -8.0989
Max Act: 8.0989. Min Act: -0.1700
Data Index: 5641001 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0989. Min Range: -8.0989
Max Act: 8.0989. Min Act: -0.1700
Data Index: 1531376 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0989. Min Range: -8.0989
Max Act: 8.0364. Min Act: -0.1700
Data Index: 2573785 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.9739. Min Act: -0.1700
Data Index: 1531334 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.8489. Min Act: -0.1700
Data Index: 6229458 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.8489. Min Act: -0.1700
Data Index: 8725456 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.8489. Min Act: -0.1700
Data Index: 667099 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.7864. Min Act: -0.1700
Data Index: 7942960 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.7864. Min Act: -0.1700
Data Index: 6247174 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.7552. Min Act: -0.1700
Data Index: 1966710 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 4307308 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6302. Min Act: -0.1700
Data Index: 6224102 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 2123093 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 479489 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 3257527 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 2068229 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6927. Min Act: -0.1700
Data Index: 2027406 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 1462238 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6302. Min Act: -0.1700
Data Index: 3194838 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0989. Min Range: -8.0989
Max Act: 7.6614. Min Act: -0.1700
Data Index: 7135028 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19