Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0175. Min Range: -7.0175
Max Act: 7.0175. Min Act: -0.1700
Data Index: 3677495 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.4863. Min Act: -0.1700
Data Index: 3137529 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.4863. Min Act: -0.1700
Data Index: 7842585 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4116852 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.4238. Min Act: -0.1700
Data Index: 4418401 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3925. Min Act: -0.1700
Data Index: 6728399 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3613. Min Act: -0.1700
Data Index: 2084266 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3925. Min Act: -0.1700
Data Index: 1055575 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3613. Min Act: -0.1700
Data Index: 8421887 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3613. Min Act: -0.1700
Data Index: 1134139 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3300. Min Act: -0.1700
Data Index: 844746 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.3613. Min Act: -0.1700
Data Index: 7567147 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4655747 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.2363. Min Act: -0.1700
Data Index: 5360030 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.2675. Min Act: -0.1700
Data Index: 1975329 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.2050. Min Act: -0.1700
Data Index: 863466 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.1738. Min Act: -0.1700
Data Index: 5751565 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.2050. Min Act: -0.1700
Data Index: 943549 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.1738. Min Act: -0.1700
Data Index: 184119 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0175. Min Range: -7.0175
Max Act: 6.1738. Min Act: -0.1700
Data Index: 184120 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19