Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.8415. Min Act: -0.1700
Data Index: 190674 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.7790. Min Act: -0.1700
Data Index: 175238 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.7165. Min Act: -0.1700
Data Index: 2815035 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.4665. Min Act: -0.1700
Data Index: 5579125 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.4040. Min Act: -0.1700
Data Index: 6504128 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.4040. Min Act: -0.1700
Data Index: 6509078 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.4040. Min Act: -0.1700
Data Index: 1861859 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.2790. Min Act: -0.1700
Data Index: 776142 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.2790. Min Act: -0.1700
Data Index: 4946113 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.2790. Min Act: -0.1700
Data Index: 8766673 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.2165. Min Act: -0.1700
Data Index: 8279655 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.2165. Min Act: -0.1700
Data Index: 8829167 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.1540. Min Act: -0.1700
Data Index: 6246667 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.0915. Min Act: -0.1700
Data Index: 7003163 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.0915. Min Act: -0.1700
Data Index: 6022918 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.0915. Min Act: -0.1700
Data Index: 3872142 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8415. Min Range: -9.8415
Max Act: 8.9665. Min Act: -0.1700
Data Index: 5449468 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8415. Min Range: -9.8415
Max Act: 9.0290. Min Act: -0.1700
Data Index: 1539118 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8415. Min Range: -9.8415
Max Act: 8.9665. Min Act: -0.1700
Data Index: 5705324 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8415. Min Range: -9.8415
Max Act: 8.9040. Min Act: -0.1700
Data Index: 456465 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19