Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1259 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1089. Min Range: -3.1089
Max Act: 3.1089. Min Act: -0.1700
Data Index: 1365251 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1089. Min Range: -3.1089
Max Act: 3.0458. Min Act: -0.1700
Data Index: 1567863 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.9985. Min Act: -0.1700
Data Index: 8578812 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.9826. Min Act: -0.1700
Data Index: 4070 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1089. Min Range: -3.1089
Max Act: 3.0458. Min Act: -0.1700
Data Index: 8731537 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.9826. Min Act: -0.1700
Data Index: 8071622 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.9352. Min Act: -0.1700
Data Index: 5580056 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.9193. Min Act: -0.1700
Data Index: 8492827 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8717. Min Act: -0.1700
Data Index: 1487206 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8876. Min Act: -0.1700
Data Index: 1503340 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8559. Min Act: -0.1700
Data Index: 328013 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8400. Min Act: -0.1700
Data Index: 7846974 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8559. Min Act: -0.1700
Data Index: 7853801 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8400. Min Act: -0.1700
Data Index: 346925 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8241. Min Act: -0.1700
Data Index: 1472412 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8559. Min Act: -0.1700
Data Index: 7043023 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8400. Min Act: -0.1700
Data Index: 4958172 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8241. Min Act: -0.1700
Data Index: 7713377 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8082. Min Act: -0.1700
Data Index: 1682707 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1089. Min Range: -3.1089
Max Act: 2.8082. Min Act: -0.1700
Data Index: 628497 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19