Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.6516. Min Act: -0.1700
Data Index: 7877177 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.4016. Min Act: -0.1700
Data Index: 5805259 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5016876 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.2453. Min Act: -0.1700
Data Index: 6087703 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.2141. Min Act: -0.1700
Data Index: 897767 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1516. Min Act: -0.1700
Data Index: 156967 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.1203. Min Act: -0.1700
Data Index: 5749942 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.0578. Min Act: -0.1700
Data Index: 2677445 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.0578. Min Act: -0.1700
Data Index: 6867078 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.0578. Min Act: -0.1700
Data Index: 5374549 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6516. Min Range: -7.6516
Max Act: 7.0266. Min Act: -0.1700
Data Index: 5001301 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9641. Min Act: -0.1700
Data Index: 785169 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9641. Min Act: -0.1700
Data Index: 7854781 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9641. Min Act: -0.1700
Data Index: 6437421 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9641. Min Act: -0.1700
Data Index: 8717524 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9641. Min Act: -0.1700
Data Index: 4152691 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9328. Min Act: -0.1700
Data Index: 3412007 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.8703. Min Act: -0.1700
Data Index: 1573629 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9016. Min Act: -0.1700
Data Index: 7640890 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6516. Min Range: -7.6516
Max Act: 6.9016. Min Act: -0.1700
Data Index: 7086550 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19