Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.7864. Min Act: -0.1700
Data Index: 6664250 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.6926. Min Act: -0.1700
Data Index: 3672083 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.5989. Min Act: -0.1700
Data Index: 7960685 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.6301. Min Act: -0.1700
Data Index: 1137017 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.5051. Min Act: -0.1700
Data Index: 4678816 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.4114. Min Act: -0.1700
Data Index: 423399 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.3489. Min Act: -0.1700
Data Index: 6271894 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2864. Min Act: -0.1700
Data Index: 8079162 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2551. Min Act: -0.1700
Data Index: 4025278 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2239. Min Act: -0.1700
Data Index: 8076063 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2239. Min Act: -0.1700
Data Index: 7881336 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2239. Min Act: -0.1700
Data Index: 44745 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.2239. Min Act: -0.1700
Data Index: 4117565 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.1926. Min Act: -0.1700
Data Index: 8290790 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.1614. Min Act: -0.1700
Data Index: 5957213 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.1614. Min Act: -0.1700
Data Index: 7163271 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.1301. Min Act: -0.1700
Data Index: 4906216 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.1614. Min Act: -0.1700
Data Index: 3544147 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.0989. Min Act: -0.1700
Data Index: 5267481 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7864. Min Range: -7.7864
Max Act: 7.0676. Min Act: -0.1700
Data Index: 6205735 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19