Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.4594. Min Act: -0.1700
Data Index: 5916459 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.2719. Min Act: -0.1700
Data Index: 5504404 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.1781. Min Act: -0.1700
Data Index: 7814893 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.1156. Min Act: -0.1700
Data Index: 3994650 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.0844. Min Act: -0.1700
Data Index: 7237314 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.0531. Min Act: -0.1700
Data Index: 7642207 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.0219. Min Act: -0.1700
Data Index: 8827871 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4594. Min Range: -8.4594
Max Act: 8.0219. Min Act: -0.1700
Data Index: 1447959 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.9594. Min Act: -0.1700
Data Index: 3453683 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.9594. Min Act: -0.1700
Data Index: 5921579 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8969. Min Act: -0.1700
Data Index: 245388 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8969. Min Act: -0.1700
Data Index: 6741737 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.9281. Min Act: -0.1700
Data Index: 5856571 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8656. Min Act: -0.1700
Data Index: 4501564 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8656. Min Act: -0.1700
Data Index: 7700833 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8656. Min Act: -0.1700
Data Index: 2665256 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8656. Min Act: -0.1700
Data Index: 6634376 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8344. Min Act: -0.1700
Data Index: 3530849 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8344. Min Act: -0.1700
Data Index: 8009740 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4594. Min Range: -8.4594
Max Act: 7.8031. Min Act: -0.1700
Data Index: 6282281 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19