Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.8460. Min Act: -0.1700
Data Index: 7402512 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.8460. Min Act: -0.1700
Data Index: 5400775 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4986243 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4020425 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7835. Min Act: -0.1700
Data Index: 2174003 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 1506736 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 61508 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 7162550 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6256970 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 7396731 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7210. Min Act: -0.1700
Data Index: 8329062 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 3582826 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7523. Min Act: -0.1700
Data Index: 2311421 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.7210. Min Act: -0.1700
Data Index: 6633520 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2711847 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7015348 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6585. Min Act: -0.1700
Data Index: 6459758 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6585. Min Act: -0.1700
Data Index: 3019144 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2059895 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8460. Min Range: -5.8460
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2526408 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19