Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 561 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.2696. Min Act: -0.1700
Data Index: 4480548 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.0821. Min Act: -0.1700
Data Index: 2494849 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.1446. Min Act: -0.1700
Data Index: 1992206 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.0821. Min Act: -0.1698
Data Index: 5914254 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.0821. Min Act: -0.1700
Data Index: 3829393 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.9571. Min Act: -0.1700
Data Index: 7658234 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2696. Min Range: -11.2696
Max Act: 11.0196. Min Act: -0.1700
Data Index: 3586545 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.9571. Min Act: -0.1700
Data Index: 2930348 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.8946. Min Act: -0.1700
Data Index: 1838067 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.8946. Min Act: -0.1700
Data Index: 5111753 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7696. Min Act: -0.1700
Data Index: 7990335 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.8321. Min Act: -0.1700
Data Index: 2578876 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7696. Min Act: -0.1700
Data Index: 8796123 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7696. Min Act: -0.1700
Data Index: 3065073 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7696. Min Act: -0.1700
Data Index: 48924 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7696. Min Act: -0.1700
Data Index: 2287421 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7071. Min Act: -0.1700
Data Index: 3309764 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.7071. Min Act: -0.1700
Data Index: 1629742 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.6446. Min Act: -0.1700
Data Index: 5941531 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2696. Min Range: -11.2696
Max Act: 10.6446. Min Act: -0.1700
Data Index: 7333616 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19