Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1028. Min Range: -4.1028
Max Act: 4.1028. Min Act: -0.1700
Data Index: 2679158 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1028. Min Range: -4.1028
Max Act: 4.0403. Min Act: -0.1700
Data Index: 904503 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1028. Min Range: -4.1028
Max Act: 4.0403. Min Act: -0.1700
Data Index: 3611905 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1028. Min Range: -4.1028
Max Act: 4.0403. Min Act: -0.1700
Data Index: 8570813 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1028. Min Range: -4.1028
Max Act: 4.0091. Min Act: -0.1700
Data Index: 437486 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9466. Min Act: -0.1700
Data Index: 3638447 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9778. Min Act: -0.1700
Data Index: 8622840 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9466. Min Act: -0.1700
Data Index: 964909 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9153. Min Act: -0.1700
Data Index: 8720358 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8840. Min Act: -0.1700
Data Index: 8614674 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9153. Min Act: -0.1700
Data Index: 3249229 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.9153. Min Act: -0.1700
Data Index: 1061522 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8528. Min Act: -0.1700
Data Index: 776421 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8528. Min Act: -0.1700
Data Index: 2077783 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8528. Min Act: -0.1700
Data Index: 1627026 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8371. Min Act: -0.1700
Data Index: 8538949 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8215. Min Act: -0.1700
Data Index: 3709350 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8058. Min Act: -0.1700
Data Index: 6873432 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8215. Min Act: -0.1700
Data Index: 1462777 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1028. Min Range: -4.1028
Max Act: 3.8058. Min Act: -0.1700
Data Index: 7516603 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19