Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0965. Min Range: -10.0965
Max Act: 10.0965. Min Act: -0.1700
Data Index: 5814355 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.5965. Min Act: -0.1700
Data Index: 3843467 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.5340. Min Act: -0.1700
Data Index: 2335298 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.4715. Min Act: -0.1700
Data Index: 4561732 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.4715. Min Act: -0.1700
Data Index: 6989282 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.4715. Min Act: -0.1700
Data Index: 7483563 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.3465. Min Act: -0.1700
Data Index: 5208089 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2840. Min Act: -0.1700
Data Index: 6530908 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.3465. Min Act: -0.1700
Data Index: 2537391 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.3465. Min Act: -0.1700
Data Index: 2051071 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2215. Min Act: -0.1700
Data Index: 4635174 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2840. Min Act: -0.1700
Data Index: 2984073 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2215. Min Act: -0.1700
Data Index: 4827010 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2215. Min Act: -0.1700
Data Index: 7732777 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.2215. Min Act: -0.1700
Data Index: 1968494 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.1590. Min Act: -0.1700
Data Index: 8605009 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 7558346 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 2091096 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 1614012 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0965. Min Range: -10.0965
Max Act: 9.0965. Min Act: -0.1700
Data Index: 8438031 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19