Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8665. Min Range: -6.8665
Max Act: 6.8665. Min Act: -0.1700
Data Index: 4453658 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8665. Min Range: -6.8665
Max Act: 6.4602. Min Act: -0.1700
Data Index: 6009920 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8665. Min Range: -6.8665
Max Act: 6.0852. Min Act: -0.1700
Data Index: 2945085 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8665. Min Range: -6.8665
Max Act: 6.0852. Min Act: -0.1700
Data Index: 5060639 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8665. Min Range: -6.8665
Max Act: 6.0540. Min Act: -0.1700
Data Index: 4547091 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.9915. Min Act: -0.1700
Data Index: 4228824 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.8977. Min Act: -0.1700
Data Index: 7138044 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.9290. Min Act: -0.1700
Data Index: 6876284 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.9290. Min Act: -0.1700
Data Index: 6524538 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.8665. Min Act: -0.1700
Data Index: 5508617 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.8665. Min Act: -0.1700
Data Index: 3362515 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.8040. Min Act: -0.1700
Data Index: 1827559 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.8040. Min Act: -0.1700
Data Index: 562256 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.7727. Min Act: -0.1700
Data Index: 4398807 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.7727. Min Act: -0.1700
Data Index: 4737850 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.7415. Min Act: -0.1700
Data Index: 6220087 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.7102. Min Act: -0.1700
Data Index: 6122145 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.6790. Min Act: -0.1700
Data Index: 3920405 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.6790. Min Act: -0.1700
Data Index: 5949827 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8665. Min Range: -6.8665
Max Act: 5.6790. Min Act: -0.1700
Data Index: 5371314 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19