Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2468. Min Range: -6.2468
Max Act: 6.2468. Min Act: -0.1700
Data Index: 7060400 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.4031. Min Act: -0.1700
Data Index: 946076 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.3406. Min Act: -0.1700
Data Index: 8102521 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.3406. Min Act: -0.1700
Data Index: 6513573 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.2781. Min Act: -0.1700
Data Index: 8492372 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.2781. Min Act: -0.1700
Data Index: 4674792 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.2156. Min Act: -0.1700
Data Index: 2486394 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1843. Min Act: -0.1700
Data Index: 7788731 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1843. Min Act: -0.1700
Data Index: 4277614 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1531. Min Act: -0.1700
Data Index: 6673407 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1843. Min Act: -0.1700
Data Index: 155125 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1531. Min Act: -0.1700
Data Index: 7481233 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1120771 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.1218. Min Act: -0.1700
Data Index: 7652067 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 6458437 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 1764810 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 4302046 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 2214848 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0906. Min Act: -0.1700
Data Index: 2188492 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2468. Min Range: -6.2468
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3126381 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19