Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.6719. Min Act: -0.1700
Data Index: 6446085 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.3281. Min Act: -0.1700
Data Index: 7121815 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.2969. Min Act: -0.1700
Data Index: 1694476 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.2969. Min Act: -0.1700
Data Index: 121996 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.2031. Min Act: -0.1700
Data Index: 5350869 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.0469. Min Act: -0.1700
Data Index: 8438787 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.0469. Min Act: -0.1700
Data Index: 106678 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.0156. Min Act: -0.1700
Data Index: 2172321 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6719. Min Range: -7.6719
Max Act: 7.0156. Min Act: -0.1700
Data Index: 4349225 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.9844. Min Act: -0.1700
Data Index: 2540339 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.9844. Min Act: -0.1700
Data Index: 2735225 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.9531. Min Act: -0.1700
Data Index: 1532620 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.9219. Min Act: -0.1700
Data Index: 1386084 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.9219. Min Act: -0.1700
Data Index: 5900862 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8906. Min Act: -0.1700
Data Index: 7785460 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8906. Min Act: -0.1700
Data Index: 778568 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8906. Min Act: -0.1700
Data Index: 2846696 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8594. Min Act: -0.1700
Data Index: 7886313 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8594. Min Act: -0.1700
Data Index: 7830333 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6719. Min Range: -7.6719
Max Act: 6.8281. Min Act: -0.1700
Data Index: 5481989 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19