Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.4123. Min Act: -0.1700
Data Index: 3942274 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.3185. Min Act: -0.1700
Data Index: 260115 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.1310. Min Act: -0.1700
Data Index: 6980363 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0997. Min Act: -0.1700
Data Index: 2940698 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0685. Min Act: -0.1700
Data Index: 374829 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0372. Min Act: -0.1700
Data Index: 3731649 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0685. Min Act: -0.1700
Data Index: 1973708 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0372. Min Act: -0.1700
Data Index: 368874 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0060. Min Act: -0.1700
Data Index: 4625703 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0060. Min Act: -0.1700
Data Index: 5889213 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0060. Min Act: -0.1700
Data Index: 554281 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0060. Min Act: -0.1700
Data Index: 1989230 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4123. Min Range: -4.4123
Max Act: 4.0060. Min Act: -0.1700
Data Index: 8193898 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9434. Min Act: -0.1700
Data Index: 4468459 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9747. Min Act: -0.1700
Data Index: 1976949 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9434. Min Act: -0.1700
Data Index: 2541861 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9434. Min Act: -0.1700
Data Index: 6192275 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9122. Min Act: -0.1700
Data Index: 1611946 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9434. Min Act: -0.1700
Data Index: 281525 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4123. Min Range: -4.4123
Max Act: 3.9434. Min Act: -0.1700
Data Index: 1598943 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19