Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.9670. Min Act: -0.1700
Data Index: 8703232 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.9670. Min Act: -0.1700
Data Index: 2915971 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.7795. Min Act: -0.1700
Data Index: 5106658 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.7170. Min Act: -0.1700
Data Index: 5205244 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.6545. Min Act: -0.1700
Data Index: 2187304 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5295. Min Act: -0.1700
Data Index: 7078357 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5295. Min Act: -0.1700
Data Index: 4216042 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5295. Min Act: -0.1700
Data Index: 7695339 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5920. Min Act: -0.1700
Data Index: 760818 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5295. Min Act: -0.1700
Data Index: 2290724 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.5295. Min Act: -0.1700
Data Index: 2410372 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4670. Min Act: -0.1700
Data Index: 3683375 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 1836165 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 8549693 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 3346459 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 8243510 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 711624 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 7653004 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.4045. Min Act: -0.1700
Data Index: 8701748 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9670. Min Range: -8.9670
Max Act: 8.3420. Min Act: -0.1700
Data Index: 565424 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19