Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1311. Min Range: -8.1311
Max Act: 8.1311. Min Act: -0.1700
Data Index: 4990259 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1311. Min Range: -8.1311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 1528423 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1311. Min Range: -8.1311
Max Act: 8.0061. Min Act: -0.1700
Data Index: 7522924 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.9436. Min Act: -0.1700
Data Index: 8533150 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.9436. Min Act: -0.1700
Data Index: 3458984 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.8811. Min Act: -0.1700
Data Index: 7432128 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.9436. Min Act: -0.1700
Data Index: 2134165 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.8186. Min Act: -0.1700
Data Index: 436192 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.8186. Min Act: -0.1700
Data Index: 7400696 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 6134056 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 5332929 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 682308 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 8047586 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 7117518 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.7561. Min Act: -0.1700
Data Index: 2753752 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.6311. Min Act: -0.1700
Data Index: 5551153 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.6311. Min Act: -0.1700
Data Index: 8505402 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.6311. Min Act: -0.1700
Data Index: 7424618 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.6311. Min Act: -0.1700
Data Index: 819783 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1311. Min Range: -8.1311
Max Act: 7.5686. Min Act: -0.1700
Data Index: 1695134 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19