Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.4312. Min Act: -0.1700
Data Index: 678132 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.3687. Min Act: -0.1700
Data Index: 2147612 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.2437. Min Act: -0.1700
Data Index: 5526070 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.1812. Min Act: -0.1700
Data Index: 185300 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.1187. Min Act: -0.1700
Data Index: 5073836 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4312. Min Range: -8.4312
Max Act: 8.0562. Min Act: -0.1700
Data Index: 201366 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9937. Min Act: -0.1700
Data Index: 3851923 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9937. Min Act: -0.1700
Data Index: 1103281 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9937. Min Act: -0.1700
Data Index: 5173112 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 5289983 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 7356506 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 2279208 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 4870265 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8687. Min Act: -0.1700
Data Index: 1970682 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8687. Min Act: -0.1700
Data Index: 3742720 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8687. Min Act: -0.1700
Data Index: 7569107 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 2738930 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8062. Min Act: -0.1700
Data Index: 5720473 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8062. Min Act: -0.1700
Data Index: 649130 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4312. Min Range: -8.4312
Max Act: 7.8687. Min Act: -0.1700
Data Index: 3525859 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19