Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.9343. Min Act: -0.1700
Data Index: 7622306 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.9343. Min Act: -0.1700
Data Index: 3444630 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.9501. Min Act: -0.1700
Data Index: 3133606 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.9343. Min Act: -0.1700
Data Index: 3639356 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8550. Min Act: -0.1700
Data Index: 1375071 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8550. Min Act: -0.1700
Data Index: 4532497 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8391. Min Act: -0.1700
Data Index: 4013184 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8232. Min Act: -0.1700
Data Index: 3971854 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8391. Min Act: -0.1700
Data Index: 951951 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8073. Min Act: -0.1700
Data Index: 1360505 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.8073. Min Act: -0.1700
Data Index: 1987800 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7754. Min Act: -0.1700
Data Index: 1890713 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7913. Min Act: -0.1700
Data Index: 4367804 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7913. Min Act: -0.1700
Data Index: 953559 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7754. Min Act: -0.1700
Data Index: 3568239 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7595. Min Act: -0.1700
Data Index: 7909121 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7754. Min Act: -0.1700
Data Index: 1969883 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7754. Min Act: -0.1700
Data Index: 4718507 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7754. Min Act: -0.1700
Data Index: 4177044 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9501. Min Range: -2.9501
Max Act: 2.7595. Min Act: -0.1700
Data Index: 6875112 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19