Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2115 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0559. Min Range: -5.0559
Max Act: 5.0559. Min Act: -0.1700
Data Index: 597713 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0559. Min Range: -5.0559
Max Act: 5.0246. Min Act: -0.1700
Data Index: 5986670 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.9621. Min Act: -0.1700
Data Index: 1580423 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.8371. Min Act: -0.1700
Data Index: 8583264 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.8059. Min Act: -0.1700
Data Index: 3107543 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7746. Min Act: -0.1700
Data Index: 7085421 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2944414 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7121. Min Act: -0.1700
Data Index: 2186608 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7431216 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7121. Min Act: -0.1700
Data Index: 5743214 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.7121. Min Act: -0.1700
Data Index: 8047135 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6496. Min Act: -0.1700
Data Index: 4970551 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6809. Min Act: -0.1700
Data Index: 3299006 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6809. Min Act: -0.1700
Data Index: 4358857 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6809. Min Act: -0.1700
Data Index: 4787229 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6496. Min Act: -0.1700
Data Index: 7792961 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6184. Min Act: -0.1700
Data Index: 1542198 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.5871. Min Act: -0.1700
Data Index: 8765853 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.6184. Min Act: -0.1700
Data Index: 8087863 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0559. Min Range: -5.0559
Max Act: 4.5871. Min Act: -0.1700
Data Index: 3496954 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19