Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.5799. Min Act: -0.1700
Data Index: 1822168 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.5487. Min Act: -0.1700
Data Index: 7869093 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.4862. Min Act: -0.1700
Data Index: 3221357 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.4862. Min Act: -0.1700
Data Index: 2426220 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.4549. Min Act: -0.1700
Data Index: 6863496 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.3612. Min Act: -0.1700
Data Index: 8777251 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.3299. Min Act: -0.1700
Data Index: 6863499 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2987. Min Act: -0.1700
Data Index: 1741950 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2987. Min Act: -0.1700
Data Index: 375764 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2987. Min Act: -0.1700
Data Index: 2816241 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.3299. Min Act: -0.1700
Data Index: 5051161 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2674. Min Act: -0.1700
Data Index: 4995537 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2362. Min Act: -0.1700
Data Index: 6228876 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2362. Min Act: -0.1700
Data Index: 3130489 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2674. Min Act: -0.1700
Data Index: 3447052 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.2049. Min Act: -0.1700
Data Index: 8419964 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.1737. Min Act: -0.1700
Data Index: 5681888 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.1424. Min Act: -0.1700
Data Index: 5047618 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.1424. Min Act: -0.1700
Data Index: 4769852 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5799. Min Range: -6.5799
Max Act: 6.1424. Min Act: -0.1700
Data Index: 3699465 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19