Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1664. Min Range: -7.1664
Max Act: 7.1664. Min Act: -0.1700
Data Index: 5629040 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.8539. Min Act: -0.1700
Data Index: 95590 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.8226. Min Act: -0.1700
Data Index: 3552117 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.7914. Min Act: -0.1700
Data Index: 2771920 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 6993921 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 862905 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 2603857 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.6351. Min Act: -0.1700
Data Index: 6064748 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.6351. Min Act: -0.1700
Data Index: 3788056 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.5726. Min Act: -0.1700
Data Index: 541166 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.5726. Min Act: -0.1700
Data Index: 3457718 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.5414. Min Act: -0.1700
Data Index: 1050300 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.5101. Min Act: -0.1700
Data Index: 6167280 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 752306 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4789. Min Act: -0.1700
Data Index: 940095 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 678333 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 4544346 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 94573 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 3092319 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1664. Min Range: -7.1664
Max Act: 6.4164. Min Act: -0.1700
Data Index: 3469973 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19