Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.9360. Min Act: -0.1700
Data Index: 6463845 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.8422. Min Act: -0.1700
Data Index: 660270 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.8422. Min Act: -0.1700
Data Index: 2352943 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.8109. Min Act: -0.1700
Data Index: 7072223 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.8422. Min Act: -0.1700
Data Index: 1037535 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.7797. Min Act: -0.1700
Data Index: 3901348 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.7484. Min Act: -0.1700
Data Index: 542764 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.7014. Min Act: -0.1700
Data Index: 5930536 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6858. Min Act: -0.1700
Data Index: 8163099 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6858. Min Act: -0.1700
Data Index: 4372214 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.7014. Min Act: -0.1700
Data Index: 5018486 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6545. Min Act: -0.1700
Data Index: 802374 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6545. Min Act: -0.1700
Data Index: 751590 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6545. Min Act: -0.1700
Data Index: 7829386 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6232. Min Act: -0.1700
Data Index: 758684 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6232. Min Act: -0.1700
Data Index: 8260861 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6232. Min Act: -0.1700
Data Index: 1276699 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.5919. Min Act: -0.1700
Data Index: 8483009 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6076. Min Act: -0.1700
Data Index: 7806854 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9360. Min Range: -3.9360
Max Act: 3.6076. Min Act: -0.1700
Data Index: 4459529 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19