Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1815. Min Range: -6.1815
Max Act: 6.1815. Min Act: -0.1700
Data Index: 8123068 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1815. Min Range: -6.1815
Max Act: 6.1190. Min Act: -0.1700
Data Index: 8622182 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.9003. Min Act: -0.1700
Data Index: 8728571 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.8065. Min Act: -0.1700
Data Index: 2606616 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.7753. Min Act: -0.1700
Data Index: 1695756 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.7128. Min Act: -0.1700
Data Index: 357550 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.6503. Min Act: -0.1700
Data Index: 8365839 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.6190. Min Act: -0.1700
Data Index: 449348 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.6190. Min Act: -0.1700
Data Index: 7007028 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.5565. Min Act: -0.1700
Data Index: 6140036 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.5565. Min Act: -0.1700
Data Index: 4888908 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.5253. Min Act: -0.1700
Data Index: 3997907 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4628. Min Act: -0.1700
Data Index: 4311704 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4628. Min Act: -0.1700
Data Index: 7548557 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4628. Min Act: -0.1700
Data Index: 4795201 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4628. Min Act: -0.1700
Data Index: 3555792 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4628. Min Act: -0.1700
Data Index: 8372090 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.4003. Min Act: -0.1700
Data Index: 3834832 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.3690. Min Act: -0.1700
Data Index: 8594093 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1815. Min Range: -6.1815
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7778764 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19