Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5428 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.6662. Min Act: -0.1700
Data Index: 203705 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.5412. Min Act: -0.1700
Data Index: 2486193 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.4162. Min Act: -0.1700
Data Index: 8580228 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.3537. Min Act: -0.1700
Data Index: 8128173 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.3225. Min Act: -0.1700
Data Index: 6835011 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2912. Min Act: -0.1700
Data Index: 570707 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2912. Min Act: -0.1700
Data Index: 7557135 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2912. Min Act: -0.1700
Data Index: 4985879 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2600. Min Act: -0.1700
Data Index: 30550 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2600. Min Act: -0.1700
Data Index: 1153965 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2600. Min Act: -0.1700
Data Index: 8219791 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2287. Min Act: -0.1700
Data Index: 4363742 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1975. Min Act: -0.1700
Data Index: 6957708 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1975. Min Act: -0.1700
Data Index: 4847871 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2287. Min Act: -0.1700
Data Index: 8245164 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.2287. Min Act: -0.1700
Data Index: 6810289 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1975. Min Act: -0.1700
Data Index: 2567363 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1662. Min Act: -0.1700
Data Index: 2331892 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1662. Min Act: -0.1700
Data Index: 7806299 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6662. Min Range: -5.6662
Max Act: 5.1662. Min Act: -0.1700
Data Index: 8241593 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19