Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4380 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1883. Min Range: -6.1883
Max Act: 6.1883. Min Act: -0.1700
Data Index: 1406373 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.9071. Min Act: -0.1700
Data Index: 4373065 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.9383. Min Act: -0.1700
Data Index: 7787040 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.8758. Min Act: -0.1700
Data Index: 8197173 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.8758. Min Act: -0.1700
Data Index: 6937648 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.8758. Min Act: -0.1700
Data Index: 3727374 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.8133. Min Act: -0.1700
Data Index: 1863680 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.7821. Min Act: -0.1700
Data Index: 36302 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.7821. Min Act: -0.1700
Data Index: 5392097 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.7508. Min Act: -0.1700
Data Index: 1829168 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.7508. Min Act: -0.1700
Data Index: 3329145 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.7196. Min Act: -0.1700
Data Index: 6557072 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6571. Min Act: -0.1700
Data Index: 6170695 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6571. Min Act: -0.1700
Data Index: 5708817 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6571. Min Act: -0.1700
Data Index: 7379445 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6258. Min Act: -0.1700
Data Index: 6141318 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6258. Min Act: -0.1700
Data Index: 7135163 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6258. Min Act: -0.1700
Data Index: 7226708 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.6258. Min Act: -0.1700
Data Index: 6524278 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1883. Min Range: -6.1883
Max Act: 5.5946. Min Act: -0.1700
Data Index: 1520021 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19