Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.4345. Min Act: -0.1700
Data Index: 1884151 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1532. Min Act: -0.1700
Data Index: 7299529 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1845. Min Act: -0.1700
Data Index: 1138078 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3180202 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1220. Min Act: -0.1700
Data Index: 7184365 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1220. Min Act: -0.1700
Data Index: 43308 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1220. Min Act: -0.1700
Data Index: 2759703 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.1220. Min Act: -0.1700
Data Index: 8014126 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0907. Min Act: -0.1700
Data Index: 7528926 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0907. Min Act: -0.1700
Data Index: 6397349 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0907. Min Act: -0.1700
Data Index: 6657577 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 5541721 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 4940230 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 6529632 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0907. Min Act: -0.1700
Data Index: 660756 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 7761368 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0282. Min Act: -0.1700
Data Index: 6184422 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0282. Min Act: -0.1700
Data Index: 4196380 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 7462839 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0282. Min Act: -0.1700
Data Index: 1470993 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19