Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.3221. Min Act: -0.1700
Data Index: 2445192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.2909. Min Act: -0.1700
Data Index: 2938388 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.2284. Min Act: -0.1700
Data Index: 245684 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.2284. Min Act: -0.1700
Data Index: 7570937 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1971. Min Act: -0.1700
Data Index: 4379463 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1971. Min Act: -0.1700
Data Index: 4314573 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1659. Min Act: -0.1700
Data Index: 1539305 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1346. Min Act: -0.1700
Data Index: 236547 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1033. Min Act: -0.1700
Data Index: 2696646 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1033. Min Act: -0.1700
Data Index: 1107624 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1033. Min Act: -0.1700
Data Index: 8156050 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1033. Min Act: -0.1700
Data Index: 2871042 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 3672036 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 4705554 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 4823289 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 3872851 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1033. Min Act: -0.1700
Data Index: 1425136 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 5856987 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0408. Min Act: -0.1700
Data Index: 1252896 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0408. Min Act: -0.1700
Data Index: 8000397 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19