Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1372 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.9564. Min Act: -0.1700
Data Index: 3095072 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.9392. Min Act: -0.1700
Data Index: 3811485 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.9392. Min Act: -0.1700
Data Index: 2547432 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.9220. Min Act: -0.1700
Data Index: 6458969 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8877. Min Act: -0.1700
Data Index: 3141008 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8963. Min Act: -0.1700
Data Index: 5116193 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8963. Min Act: -0.1700
Data Index: 4765445 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8877. Min Act: -0.1700
Data Index: 8683509 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8963. Min Act: -0.1700
Data Index: 5704899 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8877. Min Act: -0.1700
Data Index: 7485506 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8707. Min Act: -0.1700
Data Index: 6230532 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8707. Min Act: -0.1700
Data Index: 5282517 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8537. Min Act: -0.1700
Data Index: 2755523 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8537. Min Act: -0.1695
Data Index: 4642690 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8707. Min Act: -0.1700
Data Index: 7889108 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8537. Min Act: -0.1700
Data Index: 5600533 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8537. Min Act: -0.1700
Data Index: 2089603 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8452. Min Act: -0.1700
Data Index: 4654399 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8452. Min Act: -0.1700
Data Index: 1953903 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9564. Min Range: -0.9564
Max Act: 0.8452. Min Act: -0.1700
Data Index: 503790 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19