Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5279 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.1783. Min Act: -0.1700
Data Index: 7291852 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.1783. Min Act: -0.1700
Data Index: 4434420 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.1158. Min Act: -0.1700
Data Index: 1433548 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.0845. Min Act: -0.1699
Data Index: 627760 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.0533. Min Act: -0.1700
Data Index: 2803418 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1783. Min Range: -6.1783
Max Act: 6.0220. Min Act: -0.1700
Data Index: 936531 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9908. Min Act: -0.1700
Data Index: 3471030 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9908. Min Act: -0.1700
Data Index: 3064931 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9908. Min Act: -0.1700
Data Index: 2508670 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9908. Min Act: -0.1700
Data Index: 3064929 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9595. Min Act: -0.1700
Data Index: 6969717 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9595. Min Act: -0.1700
Data Index: 3039419 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9908. Min Act: -0.1700
Data Index: 269516 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9595. Min Act: -0.1700
Data Index: 4719299 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9283. Min Act: -0.1700
Data Index: 4853307 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9283. Min Act: -0.1700
Data Index: 2194638 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9283. Min Act: -0.1700
Data Index: 4008638 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9283. Min Act: -0.1700
Data Index: 3412266 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.9283. Min Act: -0.1700
Data Index: 2376974 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1783. Min Range: -6.1783
Max Act: 5.8970. Min Act: -0.1700
Data Index: 3417023 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19