Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.9394. Min Act: -0.1700
Data Index: 1538480 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.5019. Min Act: -0.1700
Data Index: 3260583 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.4394. Min Act: -0.1700
Data Index: 2818179 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.5019. Min Act: -0.1700
Data Index: 4608938 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.4394. Min Act: -0.1700
Data Index: 6319955 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.4394. Min Act: -0.1700
Data Index: 2535977 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.3769. Min Act: -0.1700
Data Index: 2505827 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.3144. Min Act: -0.1700
Data Index: 99229 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.2519. Min Act: -0.1700
Data Index: 5988898 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.2519. Min Act: -0.1700
Data Index: 3839928 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.2519. Min Act: -0.1700
Data Index: 6429737 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1894. Min Act: -0.1700
Data Index: 6692766 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1894. Min Act: -0.1700
Data Index: 1965043 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1894. Min Act: -0.1700
Data Index: 4768700 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1894. Min Act: -0.1700
Data Index: 6209767 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1894. Min Act: -0.1700
Data Index: 6720876 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1269. Min Act: -0.1700
Data Index: 1792473 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1269. Min Act: -0.1700
Data Index: 4711546 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1269. Min Act: -0.1700
Data Index: 8059480 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9394. Min Range: -10.9394
Max Act: 10.1269. Min Act: -0.1700
Data Index: 6817032 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19