Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2435 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.6505. Min Act: -0.1700
Data Index: 6092684 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.5879. Min Act: -0.1700
Data Index: 495169 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.4313. Min Act: -0.1700
Data Index: 4705837 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.4156. Min Act: -0.1700
Data Index: 495166 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3686. Min Act: -0.1700
Data Index: 992657 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3529. Min Act: -0.1700
Data Index: 1944846 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3529. Min Act: -0.1700
Data Index: 4705834 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3372. Min Act: -0.1700
Data Index: 5463749 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3372. Min Act: -0.1700
Data Index: 1393917 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3058. Min Act: -0.1700
Data Index: 4187551 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3058. Min Act: -0.1700
Data Index: 4854875 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2744. Min Act: -0.1700
Data Index: 1524442 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2744. Min Act: -0.1700
Data Index: 1944844 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2744. Min Act: -0.1700
Data Index: 704403 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2587. Min Act: -0.1700
Data Index: 260499 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2587. Min Act: -0.1700
Data Index: 7518679 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2587. Min Act: -0.1700
Data Index: 8394845 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2116. Min Act: -0.1700
Data Index: 495168 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2273. Min Act: -0.1700
Data Index: 6092683 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2116. Min Act: -0.1700
Data Index: 7882337 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19