Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2877. Min Range: -6.2877
Max Act: 6.2877. Min Act: -0.1700
Data Index: 741906 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2877. Min Range: -6.2877
Max Act: 6.0377. Min Act: -0.1700
Data Index: 8503225 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2877. Min Range: -6.2877
Max Act: 6.0065. Min Act: -0.1700
Data Index: 4675967 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.9752. Min Act: -0.1700
Data Index: 7773425 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.9440. Min Act: -0.1700
Data Index: 2337214 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.9127. Min Act: -0.1700
Data Index: 1008835 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.9440. Min Act: -0.1700
Data Index: 6657785 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8502. Min Act: -0.1700
Data Index: 3694844 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8815. Min Act: -0.1700
Data Index: 4090136 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8502. Min Act: -0.1700
Data Index: 4938100 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.7877. Min Act: -0.1700
Data Index: 8555076 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 870205 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 5786778 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 364635 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 5213978 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 390779 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.8190. Min Act: -0.1700
Data Index: 3863030 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.7877. Min Act: -0.1700
Data Index: 5525474 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.7877. Min Act: -0.1700
Data Index: 8328037 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2877. Min Range: -6.2877
Max Act: 5.7565. Min Act: -0.1700
Data Index: 2059354 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19