Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6776. Min Range: -5.6776
Max Act: 5.6776. Min Act: -0.1700
Data Index: 7983621 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6776. Min Range: -5.6776
Max Act: 5.2401. Min Act: -0.1700
Data Index: 2194732 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6776. Min Range: -5.6776
Max Act: 5.2089. Min Act: -0.1700
Data Index: 2194731 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6776. Min Range: -5.6776
Max Act: 5.2089. Min Act: -0.1700
Data Index: 1827775 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6776. Min Range: -5.6776
Max Act: 5.0839. Min Act: -0.1700
Data Index: 3931351 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.9901. Min Act: -0.1700
Data Index: 6173427 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.9589. Min Act: -0.1700
Data Index: 7986588 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.9589. Min Act: -0.1700
Data Index: 2194730 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.8651. Min Act: -0.1700
Data Index: 3550904 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.8651. Min Act: -0.1700
Data Index: 5131515 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.8339. Min Act: -0.1700
Data Index: 901112 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.8026. Min Act: -0.1700
Data Index: 3931350 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.8026. Min Act: -0.1700
Data Index: 6666080 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7321871 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7891949 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7714. Min Act: -0.1700
Data Index: 6900398 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7401. Min Act: -0.1700
Data Index: 5009253 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7401. Min Act: -0.1700
Data Index: 6190444 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7089. Min Act: -0.1700
Data Index: 626193 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6776. Min Range: -5.6776
Max Act: 4.7089. Min Act: -0.1700
Data Index: 7151567 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19