Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5371. Min Range: -8.5371
Max Act: 8.5371. Min Act: -0.1700
Data Index: 1283944 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5371. Min Range: -8.5371
Max Act: 8.2246. Min Act: -0.1700
Data Index: 1189811 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5371. Min Range: -8.5371
Max Act: 8.1309. Min Act: -0.1700
Data Index: 2165111 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5371. Min Range: -8.5371
Max Act: 8.0684. Min Act: -0.1700
Data Index: 4788523 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5371. Min Range: -8.5371
Max Act: 8.0371. Min Act: -0.1700
Data Index: 4533374 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.9121. Min Act: -0.1700
Data Index: 4892010 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.8184. Min Act: -0.1700
Data Index: 1549769 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.7871. Min Act: -0.1700
Data Index: 168209 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.7871. Min Act: -0.1700
Data Index: 1482225 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.7559. Min Act: -0.1700
Data Index: 4971764 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.7246. Min Act: -0.1700
Data Index: 5655470 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.6934. Min Act: -0.1700
Data Index: 7933296 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.6309. Min Act: -0.1700
Data Index: 8383023 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.6621. Min Act: -0.1700
Data Index: 517733 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.6309. Min Act: -0.1700
Data Index: 4422680 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.6309. Min Act: -0.1700
Data Index: 4121400 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4607320 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.5684. Min Act: -0.1700
Data Index: 6963420 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.5371. Min Act: -0.1700
Data Index: 647102 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5371. Min Range: -8.5371
Max Act: 7.5684. Min Act: -0.1700
Data Index: 1664120 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19