Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.4413. Min Act: -0.1700
Data Index: 80920 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.3475. Min Act: -0.1700
Data Index: 2846097 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.3475. Min Act: -0.1700
Data Index: 8600677 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.2225. Min Act: -0.1700
Data Index: 3526962 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.1913. Min Act: -0.1700
Data Index: 1893862 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.1913. Min Act: -0.1700
Data Index: 245416 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0975. Min Act: -0.1700
Data Index: 2635478 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0975. Min Act: -0.1700
Data Index: 5291593 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0663. Min Act: -0.1700
Data Index: 3766476 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0663. Min Act: -0.1700
Data Index: 868823 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0350. Min Act: -0.1700
Data Index: 8598691 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4413. Min Range: -6.4413
Max Act: 6.0038. Min Act: -0.1700
Data Index: 1658572 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9100. Min Act: -0.1700
Data Index: 594094 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1289992 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9413. Min Act: -0.1700
Data Index: 3867043 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9413. Min Act: -0.1700
Data Index: 520687 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9100. Min Act: -0.1700
Data Index: 2687572 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.9100. Min Act: -0.1700
Data Index: 980776 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.8788. Min Act: -0.1700
Data Index: 6891137 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4413. Min Range: -6.4413
Max Act: 5.8788. Min Act: -0.1700
Data Index: 3264607 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19