Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.2953. Min Act: -0.1700
Data Index: 441749 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.2015. Min Act: -0.1700
Data Index: 5414139 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.2015. Min Act: -0.1700
Data Index: 216043 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1697 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.0453. Min Act: -0.1700
Data Index: 3065147 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.0140. Min Act: -0.1700
Data Index: 7327899 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2953. Min Range: -6.2953
Max Act: 6.0140. Min Act: -0.1700
Data Index: 2292123 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.9828. Min Act: -0.1700
Data Index: 3724525 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2462890 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8578. Min Act: -0.1700
Data Index: 4209159 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8578. Min Act: -0.1700
Data Index: 2201478 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8578. Min Act: -0.1700
Data Index: 8511308 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.7953. Min Act: -0.1700
Data Index: 4567848 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8265. Min Act: -0.1700
Data Index: 3460165 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8265. Min Act: -0.1700
Data Index: 8279629 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8265. Min Act: -0.1700
Data Index: 37332 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.7953. Min Act: -0.1700
Data Index: 50068 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.7953. Min Act: -0.1700
Data Index: 5979980 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.8265. Min Act: -0.1700
Data Index: 1053322 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2953. Min Range: -6.2953
Max Act: 5.7953. Min Act: -0.1700
Data Index: 2856733 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19