Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1533. Min Range: -8.1533
Max Act: 8.1533. Min Act: -0.1700
Data Index: 5934429 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1533. Min Range: -8.1533
Max Act: 8.1533. Min Act: -0.1700
Data Index: 8653902 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1533. Min Range: -8.1533
Max Act: 8.1533. Min Act: -0.1700
Data Index: 861860 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1533. Min Range: -8.1533
Max Act: 8.0908. Min Act: -0.1700
Data Index: 3423512 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.9658. Min Act: -0.1700
Data Index: 3831370 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.9033. Min Act: -0.1700
Data Index: 2385530 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.9033. Min Act: -0.1700
Data Index: 6755413 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.8408. Min Act: -0.1700
Data Index: 6145928 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.7783. Min Act: -0.1700
Data Index: 5913913 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.7783. Min Act: -0.1700
Data Index: 686519 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.7470. Min Act: -0.1700
Data Index: 7712351 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.7470. Min Act: -0.1700
Data Index: 7154780 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6845. Min Act: -0.1700
Data Index: 5064284 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.7158. Min Act: -0.1700
Data Index: 3876661 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6845. Min Act: -0.1700
Data Index: 7717189 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6533. Min Act: -0.1700
Data Index: 4247119 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6533. Min Act: -0.1700
Data Index: 523565 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.5908. Min Act: -0.1700
Data Index: 6746983 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6220. Min Act: -0.1700
Data Index: 8083930 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1533. Min Range: -8.1533
Max Act: 7.6533. Min Act: -0.1700
Data Index: 5435880 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19