Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.8860. Min Act: -0.1700
Data Index: 3356331 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.5735. Min Act: -0.1700
Data Index: 8540813 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.5110. Min Act: -0.1700
Data Index: 2078132 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.4485. Min Act: -0.1700
Data Index: 7107182 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.3860. Min Act: -0.1700
Data Index: 2494918 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.3860. Min Act: -0.1700
Data Index: 6943530 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.3235. Min Act: -0.1700
Data Index: 8521705 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.2610. Min Act: -0.1700
Data Index: 3263577 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.2610. Min Act: -0.1700
Data Index: 922204 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.1985. Min Act: -0.1700
Data Index: 2384398 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.1360. Min Act: -0.1700
Data Index: 1082684 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0735. Min Act: -0.1700
Data Index: 872272 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0735. Min Act: -0.1700
Data Index: 2791045 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0735. Min Act: -0.1700
Data Index: 1682181 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 6739034 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 3972466 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 7446603 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 5170589 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 4693591 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8860. Min Range: -10.8860
Max Act: 10.0110. Min Act: -0.1700
Data Index: 5119141 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19