Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.1455. Min Act: -0.1700
Data Index: 6299254 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.1455. Min Act: -0.1700
Data Index: 3876843 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0953. Min Act: -0.1689
Data Index: 8658457 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.1121. Min Act: -0.1700
Data Index: 5118742 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0786. Min Act: -0.1700
Data Index: 4010590 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0953. Min Act: -0.1700
Data Index: 1871446 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0786. Min Act: -0.1692
Data Index: 1779978 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0786. Min Act: -0.1700
Data Index: 4117272 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0534. Min Act: -0.1700
Data Index: 2301633 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 6969510 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 1523938 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 5822394 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 4263278 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 980722 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 1312818 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0618. Min Act: -0.1700
Data Index: 7607487 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0534. Min Act: -0.1700
Data Index: 2482103 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0450. Min Act: -0.1700
Data Index: 725328 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0450. Min Act: -0.1700
Data Index: 6467847 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1455. Min Range: -2.1455
Max Act: 2.0450. Min Act: -0.1700
Data Index: 4117268 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19