Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.5304. Min Act: -0.1700
Data Index: 4347890 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.5304. Min Act: -0.1700
Data Index: 4099439 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.4054. Min Act: -0.1700
Data Index: 6459853 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.4054. Min Act: -0.1700
Data Index: 6511443 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.4054. Min Act: -0.1700
Data Index: 8611223 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.4054. Min Act: -0.1700
Data Index: 937672 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.4054. Min Act: -0.1700
Data Index: 2227800 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.3429. Min Act: -0.1700
Data Index: 7854345 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.3429. Min Act: -0.1700
Data Index: 106791 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.3429. Min Act: -0.1700
Data Index: 6689235 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.3429. Min Act: -0.1700
Data Index: 898611 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 8604977 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.3429. Min Act: -0.1700
Data Index: 5073798 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 3994499 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 3752674 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 2499039 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 2527373 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 2528129 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 4250408 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5304. Min Range: -8.5304
Max Act: 8.2804. Min Act: -0.1700
Data Index: 6715098 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19