Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2100. Min Range: -6.2100
Max Act: 6.2100. Min Act: -0.1700
Data Index: 6273139 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2100. Min Range: -6.2100
Max Act: 6.1788. Min Act: -0.1700
Data Index: 3831843 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2100. Min Range: -6.2100
Max Act: 6.0538. Min Act: -0.1700
Data Index: 5405275 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2100. Min Range: -6.2100
Max Act: 6.0225. Min Act: -0.1700
Data Index: 2814574 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2100. Min Range: -6.2100
Max Act: 6.0225. Min Act: -0.1700
Data Index: 799290 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.9913. Min Act: -0.1700
Data Index: 5907941 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.9600. Min Act: -0.1700
Data Index: 6388430 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.9288. Min Act: -0.1700
Data Index: 3293760 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.9288. Min Act: -0.1700
Data Index: 2439720 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1874104 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8975. Min Act: -0.1700
Data Index: 4207754 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8975. Min Act: -0.1700
Data Index: 2926869 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8975. Min Act: -0.1700
Data Index: 5928739 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8663. Min Act: -0.1700
Data Index: 2011591 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8350. Min Act: -0.1700
Data Index: 452748 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8350. Min Act: -0.1700
Data Index: 8508856 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8038. Min Act: -0.1700
Data Index: 4480748 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1236838 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8038. Min Act: -0.1700
Data Index: 4665438 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2100. Min Range: -6.2100
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3959565 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19