Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.5480. Min Act: -0.1700
Data Index: 4633688 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.3293. Min Act: -0.1700
Data Index: 1759521 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6106763 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6347224 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.0168. Min Act: -0.1700
Data Index: 6347225 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.0168. Min Act: -0.1700
Data Index: 6347226 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.0480. Min Act: -0.1700
Data Index: 1974986 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9543. Min Act: -0.1700
Data Index: 7812013 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9543. Min Act: -0.1700
Data Index: 5854275 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5480. Min Range: -6.5480
Max Act: 6.0168. Min Act: -0.1700
Data Index: 3590875 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9855. Min Act: -0.1700
Data Index: 5184883 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9855. Min Act: -0.1700
Data Index: 6269321 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9543. Min Act: -0.1700
Data Index: 2789386 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9543. Min Act: -0.1700
Data Index: 7279113 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9230. Min Act: -0.1700
Data Index: 2180519 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4656041 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.8918. Min Act: -0.1700
Data Index: 7603587 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.8918. Min Act: -0.1700
Data Index: 2953140 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.8918. Min Act: -0.1700
Data Index: 3762714 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5480. Min Range: -6.5480
Max Act: 5.8918. Min Act: -0.1700
Data Index: 8565626 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19