Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3940. Min Range: -6.3940
Max Act: 6.3940. Min Act: -0.1700
Data Index: 8157262 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3940. Min Range: -6.3940
Max Act: 6.1127. Min Act: -0.1700
Data Index: 1027977 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3940. Min Range: -6.3940
Max Act: 6.0502. Min Act: -0.1700
Data Index: 2502713 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3940. Min Range: -6.3940
Max Act: 6.0190. Min Act: -0.1700
Data Index: 2817628 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.9565. Min Act: -0.1700
Data Index: 8706181 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.9565. Min Act: -0.1700
Data Index: 4769403 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8940. Min Act: -0.1700
Data Index: 1747354 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8940. Min Act: -0.1700
Data Index: 4455554 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8940. Min Act: -0.1700
Data Index: 1199491 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8627. Min Act: -0.1700
Data Index: 3483308 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8627. Min Act: -0.1700
Data Index: 1221543 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8627. Min Act: -0.1700
Data Index: 8749784 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 6966027 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 1505802 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 6719809 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 2818008 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 3269531 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 4648055 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8315. Min Act: -0.1700
Data Index: 6886979 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3940. Min Range: -6.3940
Max Act: 5.8002. Min Act: -0.1700
Data Index: 7966051 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19