Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.8488. Min Act: -0.1700
Data Index: 7283157 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7551. Min Act: -0.1700
Data Index: 3800201 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7551. Min Act: -0.1700
Data Index: 8811519 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7551. Min Act: -0.1700
Data Index: 4527326 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7551. Min Act: -0.1700
Data Index: 6560356 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7551. Min Act: -0.1700
Data Index: 6061592 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7238. Min Act: -0.1700
Data Index: 336824 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7238. Min Act: -0.1700
Data Index: 5689908 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.7238. Min Act: -0.1700
Data Index: 3969137 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6926. Min Act: -0.1700
Data Index: 618653 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6926. Min Act: -0.1700
Data Index: 114697 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6926. Min Act: -0.1700
Data Index: 5396863 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6926. Min Act: -0.1700
Data Index: 7962388 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 909172 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 5883832 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 3051863 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 7476697 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 4083096 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 4407975 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8488. Min Range: -4.8488
Max Act: 4.6613. Min Act: -0.1700
Data Index: 7981096 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19