Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5621 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.7666. Min Act: -0.1700
Data Index: 6377092 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1131011 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.5791. Min Act: -0.1700
Data Index: 6951820 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.4229. Min Act: -0.1700
Data Index: 4616900 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.2979. Min Act: -0.1700
Data Index: 447662 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.2354. Min Act: -0.1700
Data Index: 6905334 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.1729. Min Act: -0.1700
Data Index: 1842734 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7666. Min Range: -7.7666
Max Act: 7.1104. Min Act: -0.1700
Data Index: 4262210 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.9854. Min Act: -0.1700
Data Index: 1601277 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.9854. Min Act: -0.1700
Data Index: 6719551 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.9541. Min Act: -0.1700
Data Index: 6802811 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.9229. Min Act: -0.1700
Data Index: 5645362 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.9229. Min Act: -0.1700
Data Index: 12242 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8604. Min Act: -0.1700
Data Index: 4939799 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8604. Min Act: -0.1700
Data Index: 7170326 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8291. Min Act: -0.1700
Data Index: 5179850 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8604. Min Act: -0.1700
Data Index: 8212135 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8291. Min Act: -0.1700
Data Index: 3180636 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8291. Min Act: -0.1700
Data Index: 5299329 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7666. Min Range: -7.7666
Max Act: 6.8291. Min Act: -0.1700
Data Index: 3410302 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19