Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 8489863 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5257. Min Act: -0.1700
Data Index: 7753862 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5257. Min Act: -0.1700
Data Index: 8498172 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5257. Min Act: -0.1700
Data Index: 4315898 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4632. Min Act: -0.1700
Data Index: 3790874 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4007. Min Act: -0.1700
Data Index: 7384632 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4007. Min Act: -0.1700
Data Index: 1514725 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4007. Min Act: -0.1700
Data Index: 1514710 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3695. Min Act: -0.1700
Data Index: 2908562 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3695. Min Act: -0.1700
Data Index: 6544928 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3382. Min Act: -0.1700
Data Index: 4790585 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3382. Min Act: -0.1700
Data Index: 7382800 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3382. Min Act: -0.1700
Data Index: 4298138 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3382. Min Act: -0.1700
Data Index: 419798 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3070. Min Act: -0.1700
Data Index: 803046 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3070. Min Act: -0.1700
Data Index: 1020208 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3070. Min Act: -0.1700
Data Index: 8555220 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.2757. Min Act: -0.1700
Data Index: 7500104 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.2757. Min Act: -0.1700
Data Index: 7687000 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.2445. Min Act: -0.1700
Data Index: 6209725 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19