Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6074 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.1287. Min Act: -0.1700
Data Index: 1308498 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.1287. Min Act: -0.1700
Data Index: 6960223 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.1287. Min Act: -0.1700
Data Index: 2739722 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.1287. Min Act: -0.1700
Data Index: 7317894 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.1287. Min Act: -0.1700
Data Index: 3429799 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.0349. Min Act: -0.1700
Data Index: 4292997 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1287. Min Range: -7.1287
Max Act: 7.0974. Min Act: -0.1700
Data Index: 4042575 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.9724. Min Act: -0.1700
Data Index: 4932094 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.8787. Min Act: -0.1700
Data Index: 3172073 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.9099. Min Act: -0.1700
Data Index: 3280226 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.8787. Min Act: -0.1700
Data Index: 2913913 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.8474. Min Act: -0.1700
Data Index: 6428608 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.8162. Min Act: -0.1700
Data Index: 6853008 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.8162. Min Act: -0.1700
Data Index: 3170892 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.7537. Min Act: -0.1700
Data Index: 4473884 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.6912. Min Act: -0.1700
Data Index: 12527 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.6599. Min Act: -0.1700
Data Index: 7522270 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.6912. Min Act: -0.1700
Data Index: 6176145 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.6599. Min Act: -0.1700
Data Index: 4269051 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1287. Min Range: -7.1287
Max Act: 6.6287. Min Act: -0.1700
Data Index: 3057546 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19