Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.4024. Min Act: -0.1700
Data Index: 1443059 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.0899. Min Act: -0.1700
Data Index: 5245383 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1908078 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.9961. Min Act: -0.1700
Data Index: 2002264 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.9024. Min Act: -0.1700
Data Index: 1081365 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.8086. Min Act: -0.1700
Data Index: 554924 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.8086. Min Act: -0.1700
Data Index: 1967679 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.7461. Min Act: -0.1700
Data Index: 2047418 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.7461. Min Act: -0.1700
Data Index: 2650127 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.7149. Min Act: -0.1700
Data Index: 567886 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6836. Min Act: -0.1700
Data Index: 2916336 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2399501 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6836. Min Act: -0.1700
Data Index: 1042048 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6836. Min Act: -0.1700
Data Index: 4053163 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7063573 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6524. Min Act: -0.1700
Data Index: 1206069 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6524. Min Act: -0.1700
Data Index: 950506 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6211. Min Act: -0.1700
Data Index: 2976015 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6211. Min Act: -0.1700
Data Index: 2919882 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4024. Min Range: -5.4024
Max Act: 4.6211. Min Act: -0.1700
Data Index: 3501728 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19