Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.5868. Min Act: -0.1700
Data Index: 3099578 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 439612 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.4306. Min Act: -0.1700
Data Index: 5277145 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3993. Min Act: -0.1700
Data Index: 7619881 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3681. Min Act: -0.1700
Data Index: 2212759 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3681. Min Act: -0.1700
Data Index: 1811603 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3681. Min Act: -0.1700
Data Index: 6969016 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3368. Min Act: -0.1700
Data Index: 6949594 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3368. Min Act: -0.1700
Data Index: 7934483 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8315845 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.3056. Min Act: -0.1700
Data Index: 3172572 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2743. Min Act: -0.1700
Data Index: 3611439 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2431. Min Act: -0.1700
Data Index: 5422625 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2431. Min Act: -0.1700
Data Index: 1087356 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2431. Min Act: -0.1700
Data Index: 2001271 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.1806. Min Act: -0.1700
Data Index: 7104888 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2118. Min Act: -0.1700
Data Index: 7375671 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2431. Min Act: -0.1700
Data Index: 6264761 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2118. Min Act: -0.1700
Data Index: 884035 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.2118. Min Act: -0.1700
Data Index: 6949591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19