Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6296 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.9674. Min Act: -0.1700
Data Index: 5311855 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.6549. Min Act: -0.1700
Data Index: 6057515 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.3424. Min Act: -0.1700
Data Index: 1156678 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.3424. Min Act: -0.1700
Data Index: 3533521 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.2799. Min Act: -0.1700
Data Index: 8770960 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.2174. Min Act: -0.1700
Data Index: 261856 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.2174. Min Act: -0.1700
Data Index: 8607106 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 8023706 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 4500277 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 4946234 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.2174. Min Act: -0.1700
Data Index: 1648355 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 5930603 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 7391008 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.1549. Min Act: -0.1700
Data Index: 5406660 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 6388757 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 5454041 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 4107590 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 2544134 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 1066877 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9674. Min Range: -9.9674
Max Act: 9.0924. Min Act: -0.1700
Data Index: 1239068 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19