Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0210. Min Range: -6.0210
Max Act: 6.0210. Min Act: -0.1700
Data Index: 576504 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.9897. Min Act: -0.1700
Data Index: 8339548 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.9272. Min Act: -0.1700
Data Index: 1064074 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8647. Min Act: -0.1700
Data Index: 4450559 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8647. Min Act: -0.1700
Data Index: 1486211 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8647. Min Act: -0.1700
Data Index: 6791273 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8647. Min Act: -0.1700
Data Index: 4293361 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8335. Min Act: -0.1700
Data Index: 3388717 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8335. Min Act: -0.1700
Data Index: 948764 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8335. Min Act: -0.1700
Data Index: 8424668 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8022. Min Act: -0.1700
Data Index: 1337495 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8022. Min Act: -0.1700
Data Index: 5136714 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8022. Min Act: -0.1700
Data Index: 8691029 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.8022. Min Act: -0.1700
Data Index: 7399519 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.7397. Min Act: -0.1700
Data Index: 604887 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.7397. Min Act: -0.1700
Data Index: 5246822 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.7397. Min Act: -0.1700
Data Index: 8051742 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.6772. Min Act: -0.1700
Data Index: 8117962 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.6772. Min Act: -0.1700
Data Index: 7100776 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0210. Min Range: -6.0210
Max Act: 5.6772. Min Act: -0.1700
Data Index: 7299686 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19