Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.1075. Min Act: -0.1700
Data Index: 8067963 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.0760. Min Act: -0.1700
Data Index: 4033479 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.0760. Min Act: -0.1700
Data Index: 2850975 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.0602. Min Act: -0.1700
Data Index: 4997365 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.0760. Min Act: -0.1700
Data Index: 3672639 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1075. Min Range: -3.1075
Max Act: 3.0129. Min Act: -0.1700
Data Index: 3436890 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9971. Min Act: -0.1700
Data Index: 2355444 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9971. Min Act: -0.1700
Data Index: 3292343 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9971. Min Act: -0.1700
Data Index: 3462264 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9655. Min Act: -0.1700
Data Index: 3149199 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9813. Min Act: -0.1700
Data Index: 7645201 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9655. Min Act: -0.1700
Data Index: 1316465 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9496. Min Act: -0.1700
Data Index: 537879 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9655. Min Act: -0.1700
Data Index: 59986 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9655. Min Act: -0.1700
Data Index: 3873033 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9338. Min Act: -0.1700
Data Index: 5262888 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9338. Min Act: -0.1700
Data Index: 1741046 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9338. Min Act: -0.1700
Data Index: 3510671 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9179. Min Act: -0.1700
Data Index: 7032029 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1075. Min Range: -3.1075
Max Act: 2.9338. Min Act: -0.1700
Data Index: 3251767 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19