Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3037. Min Range: -6.3037
Max Act: 6.3037. Min Act: -0.1700
Data Index: 3049949 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3037. Min Range: -6.3037
Max Act: 6.2412. Min Act: -0.1700
Data Index: 7068845 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3037. Min Range: -6.3037
Max Act: 6.0537. Min Act: -0.1700
Data Index: 7847934 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3037. Min Range: -6.3037
Max Act: 6.0225. Min Act: -0.1700
Data Index: 439533 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.9600. Min Act: -0.1700
Data Index: 3063177 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.8662. Min Act: -0.1700
Data Index: 4193878 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.8350. Min Act: -0.1700
Data Index: 1391633 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.8037. Min Act: -0.1700
Data Index: 2605074 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.7725. Min Act: -0.1700
Data Index: 6698207 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.7412. Min Act: -0.1700
Data Index: 914538 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.7725. Min Act: -0.1700
Data Index: 2605075 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.6787. Min Act: -0.1700
Data Index: 6265393 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.6475. Min Act: -0.1700
Data Index: 6777398 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.5850. Min Act: -0.1700
Data Index: 3049948 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.5850. Min Act: -0.1700
Data Index: 6698206 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.5225. Min Act: -0.1700
Data Index: 6922491 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.4912. Min Act: -0.1700
Data Index: 1254683 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.4912. Min Act: -0.1700
Data Index: 5603214 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.4600. Min Act: -0.1700
Data Index: 5119688 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3037. Min Range: -6.3037
Max Act: 5.4600. Min Act: -0.1700
Data Index: 349612 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19