Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 377 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.2401. Min Act: -0.1700
Data Index: 7433438 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.2089. Min Act: -0.1700
Data Index: 7673194 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.1151. Min Act: -0.1700
Data Index: 2962094 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0839. Min Act: -0.1700
Data Index: 957449 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0839. Min Act: -0.1700
Data Index: 6474260 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.1151. Min Act: -0.1700
Data Index: 3194280 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0526. Min Act: -0.1700
Data Index: 6339436 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0526. Min Act: -0.1700
Data Index: 8363570 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9901. Min Act: -0.1700
Data Index: 4476517 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0214. Min Act: -0.1700
Data Index: 3512502 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0526. Min Act: -0.1700
Data Index: 4476516 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0214. Min Act: -0.1700
Data Index: 6339439 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2401. Min Range: -6.2401
Max Act: 6.0214. Min Act: -0.1700
Data Index: 6339435 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9901. Min Act: -0.1700
Data Index: 545486 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9901. Min Act: -0.1700
Data Index: 852323 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9901. Min Act: -0.1700
Data Index: 6268626 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9589. Min Act: -0.1700
Data Index: 5823393 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9589. Min Act: -0.1700
Data Index: 6339438 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9276. Min Act: -0.1700
Data Index: 5013949 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2401. Min Range: -6.2401
Max Act: 5.9589. Min Act: -0.1700
Data Index: 532373 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19