Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2709. Min Range: -5.2709
Max Act: 5.2709. Min Act: -0.1700
Data Index: 6080081 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.7709. Min Act: -0.1700
Data Index: 4104582 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.7709. Min Act: -0.1700
Data Index: 4126126 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.7396. Min Act: -0.1700
Data Index: 186500 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.7084. Min Act: -0.1700
Data Index: 4120591 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6771. Min Act: -0.1700
Data Index: 353263 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6771. Min Act: -0.1700
Data Index: 5565776 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6459. Min Act: -0.1700
Data Index: 4845702 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6771. Min Act: -0.1700
Data Index: 5852326 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6459. Min Act: -0.1700
Data Index: 6043923 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 3404785 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 6985308 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 3643424 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5834. Min Act: -0.1700
Data Index: 4427650 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5834. Min Act: -0.1700
Data Index: 3404781 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.6146. Min Act: -0.1700
Data Index: 1708825 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5834. Min Act: -0.1700
Data Index: 3404783 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5521. Min Act: -0.1700
Data Index: 5465850 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5521. Min Act: -0.1700
Data Index: 2628390 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2709. Min Range: -5.2709
Max Act: 4.5521. Min Act: -0.1700
Data Index: 2764655 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19