Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5684. Min Act: -0.1700
Data Index: 4284902 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5371. Min Act: -0.1700
Data Index: 8378763 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5371. Min Act: -0.1700
Data Index: 4018540 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5059. Min Act: -0.1700
Data Index: 4656976 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5059. Min Act: -0.1700
Data Index: 2219612 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4121. Min Act: -0.1700
Data Index: 3728544 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4121. Min Act: -0.1700
Data Index: 8569490 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4121. Min Act: -0.1700
Data Index: 3178656 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4434. Min Act: -0.1700
Data Index: 1751971 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3809. Min Act: -0.1700
Data Index: 513492 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3496. Min Act: -0.1700
Data Index: 7977350 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4121. Min Act: -0.1700
Data Index: 6014921 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4121. Min Act: -0.1700
Data Index: 6606302 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3809. Min Act: -0.1700
Data Index: 3887258 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3809. Min Act: -0.1700
Data Index: 8375444 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3184. Min Act: -0.1700
Data Index: 2332156 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4096232 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1138186 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4274269 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3184. Min Act: -0.1700
Data Index: 1471895 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19