Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3872. Min Range: -6.3872
Max Act: 6.3872. Min Act: -0.1700
Data Index: 6363023 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3872. Min Range: -6.3872
Max Act: 6.1372. Min Act: -0.1700
Data Index: 5776222 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3872. Min Range: -6.3872
Max Act: 6.1059. Min Act: -0.1700
Data Index: 7252052 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.9184. Min Act: -0.1700
Data Index: 8544757 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.8872. Min Act: -0.1700
Data Index: 3477026 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.8247. Min Act: -0.1700
Data Index: 7414367 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.8247. Min Act: -0.1700
Data Index: 6863151 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.8559. Min Act: -0.1700
Data Index: 8181581 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.8247. Min Act: -0.1700
Data Index: 1936074 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.7622. Min Act: -0.1700
Data Index: 7252051 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.7622. Min Act: -0.1700
Data Index: 954586 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.6997. Min Act: -0.1700
Data Index: 1666953 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.6684. Min Act: -0.1700
Data Index: 3119157 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.6372. Min Act: -0.1700
Data Index: 5622895 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.6372. Min Act: -0.1700
Data Index: 135044 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 239821 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2387923 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.5434. Min Act: -0.1700
Data Index: 4917796 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 4305180 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3872. Min Range: -6.3872
Max Act: 5.5747. Min Act: -0.1700
Data Index: 7223162 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19