Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4778 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1752. Min Range: -4.1752
Max Act: 4.1752. Min Act: -0.1700
Data Index: 745727 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1752. Min Range: -4.1752
Max Act: 4.0814. Min Act: -0.1700
Data Index: 294661 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1752. Min Range: -4.1752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 3770414 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1752. Min Range: -4.1752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 7325429 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1752. Min Range: -4.1752
Max Act: 4.0189. Min Act: -0.1700
Data Index: 7236257 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.9876. Min Act: -0.1700
Data Index: 7317028 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.9876. Min Act: -0.1700
Data Index: 7052697 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.8313. Min Act: -0.1700
Data Index: 418865 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.8313. Min Act: -0.1700
Data Index: 3076070 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.8313. Min Act: -0.1700
Data Index: 6148122 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7844. Min Act: -0.1700
Data Index: 7749795 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7688. Min Act: -0.1700
Data Index: 8446640 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7688. Min Act: -0.1700
Data Index: 2279292 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7531. Min Act: -0.1700
Data Index: 1610054 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7218. Min Act: -0.1700
Data Index: 2055511 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7375. Min Act: -0.1700
Data Index: 336093 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7531. Min Act: -0.1700
Data Index: 2127731 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7218. Min Act: -0.1700
Data Index: 4881670 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.7062. Min Act: -0.1700
Data Index: 8005017 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1752. Min Range: -4.1752
Max Act: 3.6906. Min Act: -0.1700
Data Index: 2672191 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19