Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.4545. Min Act: -0.1700
Data Index: 4797014 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.3607. Min Act: -0.1700
Data Index: 6123865 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.3607. Min Act: -0.1700
Data Index: 1368039 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.2357. Min Act: -0.1700
Data Index: 5028766 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.1732. Min Act: -0.1700
Data Index: 1718386 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.1420. Min Act: -0.1700
Data Index: 1432513 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.0795. Min Act: -0.1700
Data Index: 7690161 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.0795. Min Act: -0.1700
Data Index: 7199468 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.0795. Min Act: -0.1700
Data Index: 6381497 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4545. Min Range: -6.4545
Max Act: 6.0482. Min Act: -0.1700
Data Index: 19605 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.9857. Min Act: -0.1700
Data Index: 5818878 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.9545. Min Act: -0.1700
Data Index: 1468216 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.9232. Min Act: -0.1700
Data Index: 3109194 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.9232. Min Act: -0.1700
Data Index: 5061148 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8920. Min Act: -0.1700
Data Index: 6686503 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8920. Min Act: -0.1700
Data Index: 4449174 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8607. Min Act: -0.1700
Data Index: 8765429 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8607. Min Act: -0.1700
Data Index: 7220097 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8295. Min Act: -0.1700
Data Index: 781548 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4545. Min Range: -6.4545
Max Act: 5.8295. Min Act: -0.1700
Data Index: 6221685 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19