Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2336 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5565. Min Range: -5.5565
Max Act: 5.5565. Min Act: -0.1700
Data Index: 3284787 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5565. Min Range: -5.5565
Max Act: 5.1503. Min Act: -0.1700
Data Index: 5459687 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5565. Min Range: -5.5565
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4226852 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5565. Min Range: -5.5565
Max Act: 5.0253. Min Act: -0.1700
Data Index: 8750175 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9940. Min Act: -0.1700
Data Index: 2691515 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9628. Min Act: -0.1700
Data Index: 5450325 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9628. Min Act: -0.1700
Data Index: 8229111 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7934983 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9003. Min Act: -0.1700
Data Index: 4581783 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.9003. Min Act: -0.1700
Data Index: 4607943 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8690. Min Act: -0.1700
Data Index: 6372868 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8690. Min Act: -0.1700
Data Index: 6677259 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 5806313 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8378. Min Act: -0.1700
Data Index: 6372683 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8378. Min Act: -0.1700
Data Index: 395274 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 7322700 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 2835615 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 3933187 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 6489418 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5565. Min Range: -5.5565
Max Act: 4.8065. Min Act: -0.1700
Data Index: 6050201 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19