Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0131. Min Range: -5.0131
Max Act: 5.0131. Min Act: -0.1700
Data Index: 8111777 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.6068. Min Act: -0.1700
Data Index: 1760575 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.6068. Min Act: -0.1700
Data Index: 7000680 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.6068. Min Act: -0.1700
Data Index: 4810264 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.6068. Min Act: -0.1700
Data Index: 3700214 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.6068. Min Act: -0.1700
Data Index: 5301384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.5756. Min Act: -0.1700
Data Index: 2114704 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.5131. Min Act: -0.1700
Data Index: 4979182 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5363312 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.5131. Min Act: -0.1700
Data Index: 3283009 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.5131. Min Act: -0.1700
Data Index: 5784496 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4818. Min Act: -0.1700
Data Index: 6645033 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4506. Min Act: -0.1700
Data Index: 5142194 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4506. Min Act: -0.1700
Data Index: 720271 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4506. Min Act: -0.1700
Data Index: 2411329 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4506. Min Act: -0.1700
Data Index: 4503036 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4506. Min Act: -0.1700
Data Index: 4028248 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4193. Min Act: -0.1700
Data Index: 5149686 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4193. Min Act: -0.1700
Data Index: 764526 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0131. Min Range: -5.0131
Max Act: 4.4193. Min Act: -0.1700
Data Index: 245167 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19