Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 259 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2907. Min Range: -6.2907
Max Act: 6.2907. Min Act: -0.1700
Data Index: 688463 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2907. Min Range: -6.2907
Max Act: 6.2282. Min Act: -0.1700
Data Index: 8421598 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2907. Min Range: -6.2907
Max Act: 6.0407. Min Act: -0.1700
Data Index: 8732538 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8844. Min Act: -0.1700
Data Index: 5640779 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8219. Min Act: -0.1700
Data Index: 6801713 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7907. Min Act: -0.1700
Data Index: 1108783 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8219. Min Act: -0.1700
Data Index: 4370255 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7907. Min Act: -0.1700
Data Index: 6993622 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.8219. Min Act: -0.1700
Data Index: 4209073 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7594. Min Act: -0.1700
Data Index: 8284070 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7594. Min Act: -0.1700
Data Index: 8120089 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 6528773 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 2224379 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 8273980 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 2076943 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 1040267 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 752790 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 3511835 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 2973913 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2907. Min Range: -6.2907
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6013095 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19