Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4964 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.9329. Min Act: -0.1700
Data Index: 8223102 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.8078. Min Act: -0.1700
Data Index: 5232255 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.8391. Min Act: -0.1700
Data Index: 756148 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.8391. Min Act: -0.1700
Data Index: 1679958 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.8078. Min Act: -0.1700
Data Index: 6016544 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 3182854 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7765. Min Act: -0.1700
Data Index: 4200935 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7765. Min Act: -0.1700
Data Index: 6101932 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 4514556 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 4698544 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 8821043 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 1869281 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7140. Min Act: -0.1700
Data Index: 8528746 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 3325840 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 488261 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 1073126 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.6827. Min Act: -0.1700
Data Index: 303618 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7140. Min Act: -0.1700
Data Index: 2010918 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7452. Min Act: -0.1700
Data Index: 5189019 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9329. Min Range: -3.9329
Max Act: 3.7140. Min Act: -0.1700
Data Index: 283446 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19