Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4043. Min Range: -8.4043
Max Act: 8.4043. Min Act: -0.1700
Data Index: 4203565 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4043. Min Range: -8.4043
Max Act: 8.0918. Min Act: -0.1700
Data Index: 388601 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4043. Min Range: -8.4043
Max Act: 8.0918. Min Act: -0.1700
Data Index: 6743416 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.8418. Min Act: -0.1700
Data Index: 5852811 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.8106. Min Act: -0.1700
Data Index: 111179 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.8106. Min Act: -0.1700
Data Index: 4802068 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.7793. Min Act: -0.1700
Data Index: 4802067 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.7481. Min Act: -0.1700
Data Index: 8236856 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.6856. Min Act: -0.1700
Data Index: 7970903 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.6543. Min Act: -0.1700
Data Index: 5000133 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.6231. Min Act: -0.1700
Data Index: 7134022 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5918. Min Act: -0.1700
Data Index: 111177 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5918. Min Act: -0.1700
Data Index: 4505247 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5918. Min Act: -0.1700
Data Index: 1559750 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5606. Min Act: -0.1700
Data Index: 5926239 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5606. Min Act: -0.1700
Data Index: 111208 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.5293. Min Act: -0.1700
Data Index: 5729526 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.4981. Min Act: -0.1700
Data Index: 111200 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.4981. Min Act: -0.1700
Data Index: 1948158 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4043. Min Range: -8.4043
Max Act: 7.4981. Min Act: -0.1700
Data Index: 7022542 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19