Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.7765. Min Act: -0.1700
Data Index: 35111 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.7765. Min Act: -0.1700
Data Index: 8538496 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.7140. Min Act: -0.1700
Data Index: 367584 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.6828. Min Act: -0.1700
Data Index: 1303244 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.6203. Min Act: -0.1700
Data Index: 4176985 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5890. Min Act: -0.1700
Data Index: 2081569 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5890. Min Act: -0.1700
Data Index: 5015216 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5578. Min Act: -0.1699
Data Index: 2878578 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5578. Min Act: -0.1700
Data Index: 8171773 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5578. Min Act: -0.1700
Data Index: 7729020 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5578. Min Act: -0.1700
Data Index: 7170868 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 1435647 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 2644841 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 7735327 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 173127 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3002201 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 3296091 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 5623507 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.5265. Min Act: -0.1700
Data Index: 467078 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7765. Min Range: -6.7765
Max Act: 6.4953. Min Act: -0.1700
Data Index: 6264669 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19