Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1633. Min Range: -7.1633
Max Act: 7.1633. Min Act: -0.1700
Data Index: 3164445 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1633. Min Range: -7.1633
Max Act: 7.0383. Min Act: -0.1700
Data Index: 8580195 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1633. Min Range: -7.1633
Max Act: 7.0071. Min Act: -0.1700
Data Index: 229673 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 5322848 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 8434914 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 6580581 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 6875035 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 7013221 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 7866921 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8821. Min Act: -0.1700
Data Index: 7433360 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9133. Min Act: -0.1700
Data Index: 3487869 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8821. Min Act: -0.1700
Data Index: 7147813 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8821. Min Act: -0.1700
Data Index: 4529521 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8821. Min Act: -0.1700
Data Index: 8403330 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.9133. Min Act: -0.1700
Data Index: 1651580 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8196. Min Act: -0.1700
Data Index: 8817308 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.8196. Min Act: -0.1700
Data Index: 48243 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.7883. Min Act: -0.1700
Data Index: 5328822 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.7883. Min Act: -0.1700
Data Index: 670692 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1633. Min Range: -7.1633
Max Act: 6.7571. Min Act: -0.1700
Data Index: 2158375 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19