Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4515. Min Range: -5.4515
Max Act: 5.4515. Min Act: -0.1700
Data Index: 8559588 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4515. Min Range: -5.4515
Max Act: 5.0140. Min Act: -0.1700
Data Index: 327133 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.9827. Min Act: -0.1700
Data Index: 458780 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2518129 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.9202. Min Act: -0.1700
Data Index: 367372 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8890. Min Act: -0.1700
Data Index: 6905819 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8577. Min Act: -0.1700
Data Index: 4930995 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8577. Min Act: -0.1700
Data Index: 2760672 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7952. Min Act: -0.1700
Data Index: 4233225 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8265. Min Act: -0.1700
Data Index: 1056398 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8577. Min Act: -0.1700
Data Index: 2555534 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.8265. Min Act: -0.1700
Data Index: 8581027 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7952. Min Act: -0.1700
Data Index: 7642984 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7952. Min Act: -0.1700
Data Index: 1698683 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 6811251 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 6445369 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 5817757 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 461709 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 309131 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4515. Min Range: -5.4515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 537321 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19