Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4308. Min Range: -9.4308
Max Act: 9.4308. Min Act: -0.1700
Data Index: 1132137 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.7433. Min Act: -0.1700
Data Index: 1628167 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.7433. Min Act: -0.1700
Data Index: 5658949 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.8058. Min Act: -0.1700
Data Index: 4189373 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.6808. Min Act: -0.1700
Data Index: 321344 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.6808. Min Act: -0.1700
Data Index: 6475265 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.6808. Min Act: -0.1700
Data Index: 4827577 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.6183. Min Act: -0.1700
Data Index: 4939701 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.5558. Min Act: -0.1700
Data Index: 7003450 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.6183. Min Act: -0.1700
Data Index: 2998664 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 130776 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 1697548 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 7800999 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 440072 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 3832914 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 4939699 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4933. Min Act: -0.1700
Data Index: 863136 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4308. Min Act: -0.1700
Data Index: 4226269 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4308. Min Act: -0.1700
Data Index: 5460754 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4308. Min Range: -9.4308
Max Act: 8.4308. Min Act: -0.1700
Data Index: 2852435 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19