Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2267 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.6005. Min Act: -0.1700
Data Index: 5044858 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.6005. Min Act: -0.1700
Data Index: 8477189 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.6005. Min Act: -0.1700
Data Index: 2109641 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.5380. Min Act: -0.1700
Data Index: 3261470 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.5380. Min Act: -0.1700
Data Index: 4046577 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.5380. Min Act: -0.1700
Data Index: 1369104 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.4755. Min Act: -0.1700
Data Index: 6729805 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.4130. Min Act: -0.1700
Data Index: 1987971 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.3505. Min Act: -0.1700
Data Index: 8279799 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.3505. Min Act: -0.1700
Data Index: 3375191 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.3505. Min Act: -0.1700
Data Index: 2535586 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2880. Min Act: -0.1700
Data Index: 7913158 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2880. Min Act: -0.1700
Data Index: 6797942 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2880. Min Act: -0.1700
Data Index: 2715180 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2880. Min Act: -0.1700
Data Index: 5451684 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2255. Min Act: -0.1700
Data Index: 4831633 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2255. Min Act: -0.1700
Data Index: 2109130 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2255. Min Act: -0.1700
Data Index: 6504368 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2255. Min Act: -0.1700
Data Index: 3861960 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6005. Min Range: -8.6005
Max Act: 8.2255. Min Act: -0.1700
Data Index: 2706678 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19