Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5578 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.2390. Min Act: -0.1700
Data Index: 6960378 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.1140. Min Act: -0.1700
Data Index: 6960375 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 3195475 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 6181778 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 7648936 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 6960379 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 3144689 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 8676045 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0828. Min Act: -0.1700
Data Index: 6960381 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0515. Min Act: -0.1700
Data Index: 5919311 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0515. Min Act: -0.1700
Data Index: 6899260 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0515. Min Act: -0.1700
Data Index: 2247846 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0203. Min Act: -0.1700
Data Index: 6937393 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0203. Min Act: -0.1700
Data Index: 2498561 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0203. Min Act: -0.1700
Data Index: 8412544 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0515. Min Act: -0.1700
Data Index: 8091534 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0515. Min Act: -0.1700
Data Index: 6691929 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2390. Min Range: -5.2390
Max Act: 5.0203. Min Act: -0.1700
Data Index: 7813684 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2390. Min Range: -5.2390
Max Act: 4.9890. Min Act: -0.1700
Data Index: 541278 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2390. Min Range: -5.2390
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6098780 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19