Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.7448. Min Act: -0.1700
Data Index: 4967919 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.4323. Min Act: -0.1700
Data Index: 1360417 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.4323. Min Act: -0.1700
Data Index: 7132257 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.3698. Min Act: -0.1700
Data Index: 7863751 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.3698. Min Act: -0.1700
Data Index: 1673130 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.3073. Min Act: -0.1700
Data Index: 4456315 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 1839967 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 8722857 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 700950 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 3781814 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 6216034 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.2448. Min Act: -0.1700
Data Index: 8151944 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 4275514 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 6233399 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 8529513 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 6744721 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 4723419 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 4095851 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1823. Min Act: -0.1700
Data Index: 1828690 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7448. Min Range: -9.7448
Max Act: 9.1198. Min Act: -0.1700
Data Index: 5910700 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19