Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.3519. Min Act: -0.1700
Data Index: 7375913 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.3207. Min Act: -0.1700
Data Index: 3695436 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3304271 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.2269. Min Act: -0.1700
Data Index: 5054874 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1956. Min Act: -0.1700
Data Index: 5720178 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 5850717 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1956. Min Act: -0.1700
Data Index: 2890054 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 338777 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1331. Min Act: -0.1700
Data Index: 6472166 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 3650483 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 35178 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1331. Min Act: -0.1700
Data Index: 8610486 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1331. Min Act: -0.1700
Data Index: 5926337 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1331. Min Act: -0.1700
Data Index: 3803779 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1019. Min Act: -0.1700
Data Index: 4783701 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1331. Min Act: -0.1700
Data Index: 1164384 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1019. Min Act: -0.1700
Data Index: 5987626 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.1019. Min Act: -0.1700
Data Index: 8328189 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.0706. Min Act: -0.1700
Data Index: 4958302 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3519. Min Range: -4.3519
Max Act: 4.0706. Min Act: -0.1700
Data Index: 4856360 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19