Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1230. Min Range: -7.1230
Max Act: 7.1230. Min Act: -0.1700
Data Index: 6568332 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1230. Min Range: -7.1230
Max Act: 7.1230. Min Act: -0.1700
Data Index: 5615068 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1230. Min Range: -7.1230
Max Act: 7.0292. Min Act: -0.1700
Data Index: 8610299 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.9667. Min Act: -0.1700
Data Index: 4078605 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 5096851 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 3748922 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.9042. Min Act: -0.1700
Data Index: 8533013 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.8105. Min Act: -0.1700
Data Index: 1125023 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.7167. Min Act: -0.1700
Data Index: 7854482 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.7167. Min Act: -0.1700
Data Index: 3808872 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2085942 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.6855. Min Act: -0.1700
Data Index: 872441 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.6542. Min Act: -0.1700
Data Index: 3850509 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.6542. Min Act: -0.1700
Data Index: 1921488 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.6230. Min Act: -0.1700
Data Index: 2788723 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.5917. Min Act: -0.1700
Data Index: 2087000 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.5917. Min Act: -0.1700
Data Index: 46302 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.5917. Min Act: -0.1700
Data Index: 5373291 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.5292. Min Act: -0.1700
Data Index: 4358451 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1230. Min Range: -7.1230
Max Act: 6.5292. Min Act: -0.1700
Data Index: 3574417 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19