Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.1028. Min Act: -0.1700
Data Index: 5747309 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.1028. Min Act: -0.1700
Data Index: 8560543 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.1028. Min Act: -0.1700
Data Index: 1331223 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0716. Min Act: -0.1700
Data Index: 3109763 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0716. Min Act: -0.1700
Data Index: 4449841 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0403. Min Act: -0.1700
Data Index: 358168 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0403. Min Act: -0.1700
Data Index: 8013025 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0091. Min Act: -0.1700
Data Index: 5589973 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0091. Min Act: -0.1700
Data Index: 5814734 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0091. Min Act: -0.1700
Data Index: 1820820 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0403. Min Act: -0.1700
Data Index: 5175952 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1028. Min Range: -5.1028
Max Act: 5.0091. Min Act: -0.1700
Data Index: 7558662 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3983649 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9466. Min Act: -0.1700
Data Index: 647960 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9466. Min Act: -0.1700
Data Index: 5056475 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9466. Min Act: -0.1700
Data Index: 649176 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9466. Min Act: -0.1700
Data Index: 4743000 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9466. Min Act: -0.1700
Data Index: 6590124 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.8841. Min Act: -0.1700
Data Index: 33929 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1028. Min Range: -5.1028
Max Act: 4.9153. Min Act: -0.1700
Data Index: 3464905 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19