Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5494 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4690154 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5686. Min Act: -0.1700
Data Index: 1651880 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5059. Min Act: -0.1700
Data Index: 5905250 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.5216. Min Act: -0.1700
Data Index: 5097852 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4903. Min Act: -0.1700
Data Index: 4758241 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4903. Min Act: -0.1700
Data Index: 8307593 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4589. Min Act: -0.1700
Data Index: 5197201 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 7258559 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 5560753 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4433. Min Act: -0.1700
Data Index: 5752324 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 3396064 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4276. Min Act: -0.1700
Data Index: 4412234 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 6922869 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.3962. Min Act: -0.1700
Data Index: 3637142 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 4990725 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 3125273 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.3962. Min Act: -0.1700
Data Index: 1453034 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 6225645 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.4119. Min Act: -0.1700
Data Index: 3709758 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5686. Min Range: -3.5686
Max Act: 3.3649. Min Act: -0.1700
Data Index: 2720592 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19