Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3931. Min Range: -5.3931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 7111182 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.9869. Min Act: -0.1700
Data Index: 3982388 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.9869. Min Act: -0.1700
Data Index: 2375386 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.9556. Min Act: -0.1700
Data Index: 275362 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.8619. Min Act: -0.1700
Data Index: 4492938 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.8619. Min Act: -0.1700
Data Index: 3832128 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7994. Min Act: -0.1700
Data Index: 3648461 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7994. Min Act: -0.1700
Data Index: 118422 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7681. Min Act: -0.1700
Data Index: 8718972 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7369. Min Act: -0.1700
Data Index: 3487454 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7681. Min Act: -0.1700
Data Index: 5197186 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7056. Min Act: -0.1700
Data Index: 7258522 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.7056. Min Act: -0.1700
Data Index: 3799632 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 1671202 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 3471153 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 5647673 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 5824395 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 2754859 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 1693293 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3931. Min Range: -5.3931
Max Act: 4.6431. Min Act: -0.1700
Data Index: 2366306 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19