Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5234 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.7246. Min Act: -0.1700
Data Index: 3368740 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5683. Min Act: -0.1700
Data Index: 4939532 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5371. Min Act: -0.1700
Data Index: 4775228 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5371. Min Act: -0.1700
Data Index: 4229306 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7633631 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5058. Min Act: -0.1700
Data Index: 1895115 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4746. Min Act: -0.1700
Data Index: 2813903 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6108246 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4433. Min Act: -0.1700
Data Index: 3232294 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4433. Min Act: -0.1700
Data Index: 4023048 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4433. Min Act: -0.1700
Data Index: 6318778 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4433. Min Act: -0.1700
Data Index: 7261732 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4433. Min Act: -0.1700
Data Index: 1329552 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4746. Min Act: -0.1700
Data Index: 658633 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4121. Min Act: -0.1700
Data Index: 8122428 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4121. Min Act: -0.1700
Data Index: 5344698 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.3808. Min Act: -0.1700
Data Index: 1600480 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.4121. Min Act: -0.1700
Data Index: 2296416 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.3808. Min Act: -0.1700
Data Index: 4795868 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7246. Min Range: -5.7246
Max Act: 5.3808. Min Act: -0.1700
Data Index: 947371 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19