Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1254. Min Range: -6.1254
Max Act: 6.1254. Min Act: -0.1700
Data Index: 395163 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.5004. Min Act: -0.1700
Data Index: 8503282 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.4066. Min Act: -0.1700
Data Index: 7568807 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.2816. Min Act: -0.1700
Data Index: 2844916 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.2504. Min Act: -0.1700
Data Index: 5335755 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.1879. Min Act: -0.1700
Data Index: 6516079 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.1254. Min Act: -0.1700
Data Index: 1919095 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.1254. Min Act: -0.1700
Data Index: 4730679 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.1254. Min Act: -0.1700
Data Index: 6480606 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0941. Min Act: -0.1700
Data Index: 7045130 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.1254. Min Act: -0.1700
Data Index: 988520 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0629. Min Act: -0.1700
Data Index: 2813728 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0629. Min Act: -0.1700
Data Index: 4708876 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0629. Min Act: -0.1700
Data Index: 4754653 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0004. Min Act: -0.1700
Data Index: 656027 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0316. Min Act: -0.1700
Data Index: 2757243 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0316. Min Act: -0.1700
Data Index: 6772098 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0316. Min Act: -0.1700
Data Index: 7034521 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0004. Min Act: -0.1700
Data Index: 7019112 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1254. Min Range: -6.1254
Max Act: 5.0316. Min Act: -0.1700
Data Index: 379048 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19