Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2152. Min Range: -5.2152
Max Act: 5.2152. Min Act: -0.1700
Data Index: 2728116 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2152. Min Range: -5.2152
Max Act: 5.1840. Min Act: -0.1700
Data Index: 258776 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2152. Min Range: -5.2152
Max Act: 5.0902. Min Act: -0.1700
Data Index: 102830 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2152. Min Range: -5.2152
Max Act: 5.0590. Min Act: -0.1700
Data Index: 6843078 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2152. Min Range: -5.2152
Max Act: 5.0277. Min Act: -0.1700
Data Index: 897705 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.9652. Min Act: -0.1700
Data Index: 6007602 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.9340. Min Act: -0.1700
Data Index: 4880066 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.9340. Min Act: -0.1700
Data Index: 7405822 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.9027. Min Act: -0.1700
Data Index: 3846478 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8715. Min Act: -0.1700
Data Index: 2367111 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8715. Min Act: -0.1700
Data Index: 1084791 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8402. Min Act: -0.1700
Data Index: 509219 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8402. Min Act: -0.1700
Data Index: 4284985 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8402. Min Act: -0.1700
Data Index: 687744 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8402. Min Act: -0.1700
Data Index: 2543745 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8402. Min Act: -0.1700
Data Index: 6945166 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8090. Min Act: -0.1700
Data Index: 1036311 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8090. Min Act: -0.1700
Data Index: 2722287 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8090. Min Act: -0.1700
Data Index: 7788085 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2152. Min Range: -5.2152
Max Act: 4.8090. Min Act: -0.1700
Data Index: 6094784 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19