Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6228 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.6937. Min Act: -0.1700
Data Index: 6694952 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.3187. Min Act: -0.1700
Data Index: 880187 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.1937. Min Act: -0.1700
Data Index: 276539 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.1937. Min Act: -0.1700
Data Index: 7436916 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.1312. Min Act: -0.1700
Data Index: 8062148 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.0062. Min Act: -0.1700
Data Index: 2524318 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6937. Min Range: -9.6937
Max Act: 9.0062. Min Act: -0.1700
Data Index: 4759902 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8812. Min Act: -0.1700
Data Index: 1804037 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.9437. Min Act: -0.1700
Data Index: 2351626 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.9437. Min Act: -0.1700
Data Index: 6648404 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8812. Min Act: -0.1700
Data Index: 5356247 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8812. Min Act: -0.1700
Data Index: 6600494 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8812. Min Act: -0.1700
Data Index: 5593788 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8187. Min Act: -0.1700
Data Index: 2410986 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8187. Min Act: -0.1700
Data Index: 3388518 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.8187. Min Act: -0.1700
Data Index: 2789088 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.7562. Min Act: -0.1700
Data Index: 680927 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.7562. Min Act: -0.1700
Data Index: 689696 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.7562. Min Act: -0.1700
Data Index: 2958257 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6937. Min Range: -9.6937
Max Act: 8.7562. Min Act: -0.1700
Data Index: 1435233 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19