Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0031. Min Range: -5.0031
Max Act: 5.0031. Min Act: -0.1700
Data Index: 241031 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.9094. Min Act: -0.1700
Data Index: 1760525 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.9094. Min Act: -0.1700
Data Index: 4550644 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.7531. Min Act: -0.1700
Data Index: 5600771 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.7218. Min Act: -0.1700
Data Index: 2621391 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6906. Min Act: -0.1700
Data Index: 5340567 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6906. Min Act: -0.1700
Data Index: 4867638 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6593. Min Act: -0.1700
Data Index: 160925 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6593. Min Act: -0.1700
Data Index: 6301351 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6281. Min Act: -0.1700
Data Index: 1325815 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6281. Min Act: -0.1700
Data Index: 2472327 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6593. Min Act: -0.1700
Data Index: 498084 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.6593. Min Act: -0.1700
Data Index: 3386648 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5968. Min Act: -0.1700
Data Index: 6860212 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5968. Min Act: -0.1700
Data Index: 3576225 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5968. Min Act: -0.1700
Data Index: 8382788 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5656. Min Act: -0.1700
Data Index: 3463531 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5656. Min Act: -0.1700
Data Index: 392702 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5656. Min Act: -0.1700
Data Index: 4949347 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0031. Min Range: -5.0031
Max Act: 4.5968. Min Act: -0.1700
Data Index: 4001453 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19