Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.7940. Min Act: -0.1700
Data Index: 5607534 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6845. Min Act: -0.1700
Data Index: 2344526 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6532. Min Act: -0.1700
Data Index: 7999770 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6532. Min Act: -0.1700
Data Index: 753856 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6219. Min Act: -0.1700
Data Index: 6553567 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5749. Min Act: -0.1700
Data Index: 581372 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 2098413 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 2098412 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 8516305 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 4434615 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 7748601 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 1820415 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4653. Min Act: -0.1700
Data Index: 6206294 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4653. Min Act: -0.1700
Data Index: 3554586 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 8299066 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 3433950 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 4747155 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 1665064 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 5196599 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4026. Min Act: -0.1700
Data Index: 6094638 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19