Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4203. Min Range: -7.4203
Max Act: 7.4203. Min Act: -0.1700
Data Index: 3261629 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4203. Min Range: -7.4203
Max Act: 7.1703. Min Act: -0.1700
Data Index: 8324305 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4203. Min Range: -7.4203
Max Act: 7.0453. Min Act: -0.1700
Data Index: 5062726 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.9828. Min Act: -0.1700
Data Index: 7335892 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.9828. Min Act: -0.1700
Data Index: 3268442 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.9203. Min Act: -0.1700
Data Index: 1598683 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.8891. Min Act: -0.1700
Data Index: 2387202 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.8891. Min Act: -0.1700
Data Index: 860778 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.8578. Min Act: -0.1700
Data Index: 1317803 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.7328. Min Act: -0.1700
Data Index: 8392226 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.7016. Min Act: -0.1700
Data Index: 1598679 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.7016. Min Act: -0.1700
Data Index: 2630887 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.6703. Min Act: -0.1700
Data Index: 3309873 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.6078. Min Act: -0.1700
Data Index: 8129772 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.6078. Min Act: -0.1700
Data Index: 8227565 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.6078. Min Act: -0.1700
Data Index: 1975725 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 8590910 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 6598195 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 173206 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4203. Min Range: -7.4203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 7613179 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19