Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6170 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3350. Min Range: -5.3350
Max Act: 5.3350. Min Act: -0.1700
Data Index: 4983825 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3350. Min Range: -5.3350
Max Act: 5.0850. Min Act: -0.1700
Data Index: 8405355 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3350. Min Range: -5.3350
Max Act: 5.0225. Min Act: -0.1700
Data Index: 7504663 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9913. Min Act: -0.1700
Data Index: 4838799 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9600. Min Act: -0.1700
Data Index: 1639086 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9913. Min Act: -0.1700
Data Index: 4028859 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9913. Min Act: -0.1700
Data Index: 976474 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3350. Min Range: -5.3350
Max Act: 5.0225. Min Act: -0.1700
Data Index: 339224 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9600. Min Act: -0.1700
Data Index: 336014 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9288. Min Act: -0.1700
Data Index: 5608703 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9288. Min Act: -0.1700
Data Index: 5743201 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9288. Min Act: -0.1700
Data Index: 891471 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8975. Min Act: -0.1700
Data Index: 3808317 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8975. Min Act: -0.1700
Data Index: 6737992 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.9288. Min Act: -0.1700
Data Index: 4782346 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8663. Min Act: -0.1700
Data Index: 3119708 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8663. Min Act: -0.1700
Data Index: 871708 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8663. Min Act: -0.1700
Data Index: 6256987 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8663. Min Act: -0.1700
Data Index: 4294742 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3350. Min Range: -5.3350
Max Act: 4.8663. Min Act: -0.1700
Data Index: 3399492 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19