Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4428. Min Range: -5.4428
Max Act: 5.4428. Min Act: -0.1700
Data Index: 8353416 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4428. Min Range: -5.4428
Max Act: 5.4115. Min Act: -0.1700
Data Index: 3931764 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4428. Min Range: -5.4428
Max Act: 5.0365. Min Act: -0.1700
Data Index: 824971 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4428. Min Range: -5.4428
Max Act: 5.0365. Min Act: -0.1700
Data Index: 4830917 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.9428. Min Act: -0.1700
Data Index: 1220218 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.9428. Min Act: -0.1700
Data Index: 1463073 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.8803. Min Act: -0.1700
Data Index: 1487954 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.8803. Min Act: -0.1700
Data Index: 7023906 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.7865. Min Act: -0.1700
Data Index: 5670161 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.7553. Min Act: -0.1700
Data Index: 6853620 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.7553. Min Act: -0.1700
Data Index: 1600848 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.7553. Min Act: -0.1700
Data Index: 5960434 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.7240. Min Act: -0.1700
Data Index: 8772983 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2719699 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.6303. Min Act: -0.1700
Data Index: 5883217 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.6615. Min Act: -0.1700
Data Index: 5360024 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.6303. Min Act: -0.1700
Data Index: 618459 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.5990. Min Act: -0.1700
Data Index: 8170788 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.5990. Min Act: -0.1700
Data Index: 2387649 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4428. Min Range: -5.4428
Max Act: 4.5990. Min Act: -0.1700
Data Index: 6191551 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19