Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.4316. Min Act: -0.1700
Data Index: 6525632 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.3691. Min Act: -0.1700
Data Index: 4264005 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.3378. Min Act: -0.1700
Data Index: 1395555 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.2753. Min Act: -0.1700
Data Index: 4802982 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.2753. Min Act: -0.1700
Data Index: 5409996 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.2128. Min Act: -0.1700
Data Index: 4496320 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.1816. Min Act: -0.1700
Data Index: 114710 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.1503. Min Act: -0.1700
Data Index: 6488943 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.0878. Min Act: -0.1700
Data Index: 3706966 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4316. Min Range: -6.4316
Max Act: 6.0878. Min Act: -0.1700
Data Index: 1780887 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.9941. Min Act: -0.1700
Data Index: 7937236 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.9941. Min Act: -0.1700
Data Index: 836017 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.8691. Min Act: -0.1700
Data Index: 6270340 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.8691. Min Act: -0.1700
Data Index: 5722258 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.8378. Min Act: -0.1700
Data Index: 995040 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.8066. Min Act: -0.1700
Data Index: 1590641 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.8066. Min Act: -0.1700
Data Index: 8074839 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 999175 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5951567 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4316. Min Range: -6.4316
Max Act: 5.7753. Min Act: -0.1700
Data Index: 97885 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19