Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4067. Min Range: -5.4067
Max Act: 5.4067. Min Act: -0.1700
Data Index: 7099131 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.5316. Min Act: -0.1700
Data Index: 3526398 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.4691. Min Act: -0.1700
Data Index: 2546554 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.4066. Min Act: -0.1700
Data Index: 8010982 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3754. Min Act: -0.1700
Data Index: 2439373 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3754. Min Act: -0.1700
Data Index: 3775681 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3754. Min Act: -0.1700
Data Index: 7381568 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3754. Min Act: -0.1700
Data Index: 4330738 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 4420904 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 1148630 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 1321224 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 2289322 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 8495671 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3129. Min Act: -0.1700
Data Index: 2396497 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 5589301 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.3129. Min Act: -0.1700
Data Index: 8033627 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.2816. Min Act: -0.1700
Data Index: 1754199 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.2816. Min Act: -0.1700
Data Index: 1342648 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.2816. Min Act: -0.1700
Data Index: 5122582 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4067. Min Range: -5.4067
Max Act: 4.2816. Min Act: -0.1700
Data Index: 6997494 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19