Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.3185. Min Act: -0.1700
Data Index: 1633947 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2872. Min Act: -0.1700
Data Index: 7198921 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2560. Min Act: -0.1700
Data Index: 7989279 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2247. Min Act: -0.1700
Data Index: 6973937 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2247. Min Act: -0.1700
Data Index: 5840758 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1935. Min Act: -0.1700
Data Index: 3072366 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1935. Min Act: -0.1700
Data Index: 5440040 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 277926 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 7740279 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 1545741 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 5314264 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 4668457 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 385845 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 4368398 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 2874436 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 828145 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 5475826 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 1794756 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 5912446 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 4732409 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19