Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6753. Min Range: -10.6753
Max Act: 10.6753. Min Act: -0.1700
Data Index: 3235035 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6753. Min Range: -10.6753
Max Act: 10.3628. Min Act: -0.1700
Data Index: 8150510 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6753. Min Range: -10.6753
Max Act: 10.3628. Min Act: -0.1700
Data Index: 6282238 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6753. Min Range: -10.6753
Max Act: 10.1753. Min Act: -0.1700
Data Index: 6615856 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.9878. Min Act: -0.1700
Data Index: 7227829 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.9878. Min Act: -0.1700
Data Index: 2620259 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.9253. Min Act: -0.1700
Data Index: 8613011 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.9253. Min Act: -0.1700
Data Index: 4392366 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.8003. Min Act: -0.1700
Data Index: 7858594 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.8003. Min Act: -0.1700
Data Index: 7505753 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.8003. Min Act: -0.1700
Data Index: 8339280 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.8003. Min Act: -0.1700
Data Index: 5500908 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.7378. Min Act: -0.1700
Data Index: 4648465 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.7378. Min Act: -0.1700
Data Index: 3126447 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.7378. Min Act: -0.1700
Data Index: 2711647 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.7378. Min Act: -0.1700
Data Index: 6441060 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.6753. Min Act: -0.1700
Data Index: 5788950 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.6753. Min Act: -0.1700
Data Index: 1979589 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.6753. Min Act: -0.1700
Data Index: 36361 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6753. Min Range: -10.6753
Max Act: 9.6753. Min Act: -0.1700
Data Index: 4946204 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19