Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.5694. Min Act: -0.1700
Data Index: 7437758 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.5069. Min Act: -0.1700
Data Index: 3876071 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.5069. Min Act: -0.1700
Data Index: 4961622 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.4757. Min Act: -0.1700
Data Index: 875398 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.5069. Min Act: -0.1700
Data Index: 626397 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.4444. Min Act: -0.1700
Data Index: 3467134 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.4132. Min Act: -0.1700
Data Index: 7742438 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3507. Min Act: -0.1700
Data Index: 6243959 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 6929731 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 8658110 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 8405333 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 2306883 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 8553091 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2882. Min Act: -0.1700
Data Index: 3829542 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2882. Min Act: -0.1700
Data Index: 2814725 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2882. Min Act: -0.1700
Data Index: 6022757 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2569. Min Act: -0.1700
Data Index: 8495012 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2569. Min Act: -0.1700
Data Index: 5752202 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2256. Min Act: -0.1700
Data Index: 5402638 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2256. Min Act: -0.1700
Data Index: 3316287 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19