Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5889 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.8958. Min Act: -0.1700
Data Index: 1110101 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.8333. Min Act: -0.1700
Data Index: 3784597 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.7083. Min Act: -0.1700
Data Index: 2827705 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6770. Min Act: -0.1700
Data Index: 8303719 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6770. Min Act: -0.1700
Data Index: 7583544 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6458. Min Act: -0.1700
Data Index: 4430432 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6458. Min Act: -0.1700
Data Index: 2956712 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6458. Min Act: -0.1700
Data Index: 5029938 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 8698246 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 870490 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 2511736 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 1911249 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 465780 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.5833. Min Act: -0.1700
Data Index: 585702 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.6145. Min Act: -0.1700
Data Index: 432573 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.5520. Min Act: -0.1700
Data Index: 2737335 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.5520. Min Act: -0.1700
Data Index: 2523794 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.4895. Min Act: -0.1700
Data Index: 991965 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.5208. Min Act: -0.1700
Data Index: 5614416 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8958. Min Range: -4.8958
Max Act: 4.5208. Min Act: -0.1700
Data Index: 3784602 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19