Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.3940. Min Act: -0.1700
Data Index: 1991029 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.3940. Min Act: -0.1700
Data Index: 293214 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.2378. Min Act: -0.1700
Data Index: 5120026 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.1753. Min Act: -0.1700
Data Index: 8542596 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1991010 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1087860 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.1128. Min Act: -0.1700
Data Index: 5428479 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.0503. Min Act: -0.1700
Data Index: 1420009 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5511279 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3940. Min Range: -5.3940
Max Act: 5.0190. Min Act: -0.1700
Data Index: 4026768 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1188312 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5120024 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.9565. Min Act: -0.1700
Data Index: 1991015 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.9878. Min Act: -0.1700
Data Index: 7601788 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.9253. Min Act: -0.1700
Data Index: 6785171 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4952446 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.8940. Min Act: -0.1700
Data Index: 7076626 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.8940. Min Act: -0.1700
Data Index: 1991030 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.8628. Min Act: -0.1700
Data Index: 3680802 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3940. Min Range: -5.3940
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4564978 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19