Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5820 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4720. Min Range: -8.4720
Max Act: 8.4720. Min Act: -0.1700
Data Index: 6287340 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.8470. Min Act: -0.1700
Data Index: 2697779 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.6282. Min Act: -0.1700
Data Index: 3800259 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.6282. Min Act: -0.1700
Data Index: 26120 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.5970. Min Act: -0.1700
Data Index: 8284848 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.5032. Min Act: -0.1700
Data Index: 5448528 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.4407. Min Act: -0.1700
Data Index: 6160271 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.4095. Min Act: -0.1700
Data Index: 8484725 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.3782. Min Act: -0.1700
Data Index: 5048175 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.4095. Min Act: -0.1700
Data Index: 2517194 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.3470. Min Act: -0.1700
Data Index: 5632022 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2845. Min Act: -0.1700
Data Index: 8509573 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2845. Min Act: -0.1700
Data Index: 3876541 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2532. Min Act: -0.1700
Data Index: 7812143 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2220. Min Act: -0.1700
Data Index: 7464703 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2220. Min Act: -0.1700
Data Index: 6088033 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2220. Min Act: -0.1700
Data Index: 8050791 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.2220. Min Act: -0.1700
Data Index: 1993690 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.1907. Min Act: -0.1700
Data Index: 6539923 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4720. Min Range: -8.4720
Max Act: 7.1595. Min Act: -0.1700
Data Index: 4357702 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19