Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4997 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2244. Min Range: -8.2244
Max Act: 8.2244. Min Act: -0.1700
Data Index: 286918 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2244. Min Range: -8.2244
Max Act: 8.0994. Min Act: -0.1700
Data Index: 4114770 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2244. Min Range: -8.2244
Max Act: 8.0369. Min Act: -0.1700
Data Index: 4697572 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9744. Min Act: -0.1700
Data Index: 7222962 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9119. Min Act: -0.1700
Data Index: 5929312 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9119. Min Act: -0.1700
Data Index: 1210159 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.9119. Min Act: -0.1700
Data Index: 7036297 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.8182. Min Act: -0.1700
Data Index: 1464865 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.6619. Min Act: -0.1700
Data Index: 3790315 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.5369. Min Act: -0.1700
Data Index: 8499163 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.4744. Min Act: -0.1700
Data Index: 374764 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 1791391 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.3807. Min Act: -0.1700
Data Index: 1479934 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.3807. Min Act: -0.1700
Data Index: 1168802 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.3182. Min Act: -0.1700
Data Index: 4936389 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.3182. Min Act: -0.1700
Data Index: 1208893 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.2869. Min Act: -0.1700
Data Index: 6522966 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.3182. Min Act: -0.1700
Data Index: 4299454 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.2869. Min Act: -0.1700
Data Index: 5156078 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2244. Min Range: -8.2244
Max Act: 7.2557. Min Act: -0.1700
Data Index: 3826526 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19