Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1483 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3424. Min Range: -10.3424
Max Act: 10.3424. Min Act: -0.1700
Data Index: 6339373 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3424. Min Range: -10.3424
Max Act: 10.1549. Min Act: -0.1700
Data Index: 3374592 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3424. Min Range: -10.3424
Max Act: 10.0299. Min Act: -0.1700
Data Index: 409806 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.9674. Min Act: -0.1700
Data Index: 7689582 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.9049. Min Act: -0.1700
Data Index: 7653137 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.8424. Min Act: -0.1700
Data Index: 1786363 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.7799. Min Act: -0.1700
Data Index: 2263639 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.7799. Min Act: -0.1700
Data Index: 4143947 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.7174. Min Act: -0.1700
Data Index: 4903791 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.6549. Min Act: -0.1700
Data Index: 2041721 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.6549. Min Act: -0.1700
Data Index: 8753712 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.5299. Min Act: -0.1700
Data Index: 662440 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.5299. Min Act: -0.1700
Data Index: 7086824 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.5299. Min Act: -0.1700
Data Index: 1875474 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.4674. Min Act: -0.1700
Data Index: 6975614 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.5299. Min Act: -0.1700
Data Index: 4039766 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.4674. Min Act: -0.1700
Data Index: 2672077 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.4674. Min Act: -0.1700
Data Index: 1271066 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.4674. Min Act: -0.1700
Data Index: 7779240 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3424. Min Range: -10.3424
Max Act: 9.4674. Min Act: -0.1700
Data Index: 3628125 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19