Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2399 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.6643. Min Act: -0.1700
Data Index: 5312237 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.6018. Min Act: -0.1700
Data Index: 6459976 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.3518. Min Act: -0.1700
Data Index: 4963383 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.2893. Min Act: -0.1700
Data Index: 5161480 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.2268. Min Act: -0.1700
Data Index: 994818 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.2268. Min Act: -0.1700
Data Index: 145085 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.2268. Min Act: -0.1700
Data Index: 1283830 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.1643. Min Act: -0.1700
Data Index: 1954906 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.1018. Min Act: -0.1700
Data Index: 8710364 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.1018. Min Act: -0.1700
Data Index: 6825930 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.0393. Min Act: -0.1700
Data Index: 7996840 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6643. Min Range: -8.6643
Max Act: 8.0080. Min Act: -0.1700
Data Index: 2682712 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.9455. Min Act: -0.1700
Data Index: 1204965 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.9143. Min Act: -0.1700
Data Index: 6671951 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.9143. Min Act: -0.1700
Data Index: 6003391 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.8830. Min Act: -0.1700
Data Index: 6670627 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.8830. Min Act: -0.1700
Data Index: 5908882 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.8518. Min Act: -0.1700
Data Index: 4986234 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.8830. Min Act: -0.1700
Data Index: 2653935 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6643. Min Range: -8.6643
Max Act: 7.8518. Min Act: -0.1700
Data Index: 3241819 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19