Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0582. Min Range: -6.0582
Max Act: 6.0582. Min Act: -0.1700
Data Index: 456149 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.9644. Min Act: -0.1700
Data Index: 3193647 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6851508 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.9332. Min Act: -0.1700
Data Index: 7477340 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.9332. Min Act: -0.1700
Data Index: 2423809 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5455241 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8707. Min Act: -0.1700
Data Index: 4318319 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1571449 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8707. Min Act: -0.1700
Data Index: 7905832 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1659629 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8394. Min Act: -0.1700
Data Index: 5813179 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.8082. Min Act: -0.1700
Data Index: 8181951 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7769. Min Act: -0.1700
Data Index: 2814534 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7769. Min Act: -0.1700
Data Index: 5464609 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7457. Min Act: -0.1700
Data Index: 2304975 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7457. Min Act: -0.1700
Data Index: 5293704 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7457. Min Act: -0.1700
Data Index: 955189 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7457. Min Act: -0.1700
Data Index: 2304590 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7457. Min Act: -0.1700
Data Index: 1863635 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0582. Min Range: -6.0582
Max Act: 5.7144. Min Act: -0.1700
Data Index: 5890548 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19