Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5460 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.5125. Min Act: -0.1700
Data Index: 2115009 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.3562. Min Act: -0.1700
Data Index: 3143861 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.3250. Min Act: -0.1700
Data Index: 3571753 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.2312. Min Act: -0.1700
Data Index: 5383563 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.2625. Min Act: -0.1700
Data Index: 1839358 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2926669 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2447027 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.2312. Min Act: -0.1700
Data Index: 5513923 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1687. Min Act: -0.1700
Data Index: 7989733 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 5372986 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 2196555 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 8387385 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 4312516 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 3868130 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1375. Min Act: -0.1700
Data Index: 5909782 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1062. Min Act: -0.1700
Data Index: 5311180 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.0750. Min Act: -0.1700
Data Index: 1302718 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1062. Min Act: -0.1700
Data Index: 6243607 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1062. Min Act: -0.1700
Data Index: 5095188 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5125. Min Range: -4.5125
Max Act: 4.1062. Min Act: -0.1700
Data Index: 2740392 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19