Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.9188. Min Act: -0.1700
Data Index: 7857584 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.4807. Min Act: -0.1700
Data Index: 1694120 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.4181. Min Act: -0.1700
Data Index: 8658953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.3240. Min Act: -0.1700
Data Index: 7145295 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1462
Data Index: 4255847 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2926. Min Act: -0.1700
Data Index: 6486221 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1700
Data Index: 5207953 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1646
Data Index: 5479298 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1700
Data Index: 5946139 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1601
Data Index: 3884844 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2612. Min Act: -0.1700
Data Index: 663439 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.1983. Min Act: -0.1441
Data Index: 3092547 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1700
Data Index: 7076392 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1700
Data Index: 1240240 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1614
Data Index: 2807035 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1699
Data Index: 4635379 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1700
Data Index: 6298696 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1412
Data Index: 3608946 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1465
Data Index: 4044750 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9188. Min Range: -3.9188
Max Act: 3.2297. Min Act: -0.1643
Data Index: 1101834 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19