Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4056. Min Range: -5.4056
Max Act: 5.4056. Min Act: -0.1700
Data Index: 1853813 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4056. Min Range: -5.4056
Max Act: 5.1868. Min Act: -0.1700
Data Index: 303968 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4056. Min Range: -5.4056
Max Act: 5.0306. Min Act: -0.1700
Data Index: 997170 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5486156 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9368. Min Act: -0.1700
Data Index: 4866361 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6005646 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9368. Min Act: -0.1700
Data Index: 5962443 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 8210710 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 4664481 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.9056. Min Act: -0.1700
Data Index: 6997575 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.8743. Min Act: -0.1700
Data Index: 62590 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.8118. Min Act: -0.1700
Data Index: 314527 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.8118. Min Act: -0.1700
Data Index: 6874067 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 7200851 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 3778639 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 1810695 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7806. Min Act: -0.1700
Data Index: 3828541 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7493. Min Act: -0.1700
Data Index: 3251259 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7493. Min Act: -0.1700
Data Index: 7946532 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4056. Min Range: -5.4056
Max Act: 4.7181. Min Act: -0.1700
Data Index: 234503 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19