Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0705. Min Range: -5.0705
Max Act: 5.0705. Min Act: -0.1700
Data Index: 3372470 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.9767. Min Act: -0.1700
Data Index: 3412645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.9142. Min Act: -0.1700
Data Index: 4783890 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8517. Min Act: -0.1700
Data Index: 7520037 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8517. Min Act: -0.1700
Data Index: 4193133 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8205. Min Act: -0.1700
Data Index: 5764666 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8205. Min Act: -0.1700
Data Index: 5795398 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.8205. Min Act: -0.1700
Data Index: 3650539 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 665067 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 4218878 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 2973995 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8344124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 5184660 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 4834800 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7892. Min Act: -0.1700
Data Index: 7863858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 4133947 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2073043 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2745029 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 2210231 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0705. Min Range: -5.0705
Max Act: 4.7267. Min Act: -0.1700
Data Index: 4783889 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19