Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.4686. Min Act: -0.1700
Data Index: 3397566 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.4373. Min Act: -0.1700
Data Index: 1973991 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.4216. Min Act: -0.1700
Data Index: 656037 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3746. Min Act: -0.1700
Data Index: 4619378 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3746. Min Act: -0.1700
Data Index: 6770207 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 7252907 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 4538086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 6824164 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 2973295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 8764510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 8644280 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 7541357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3432. Min Act: -0.1700
Data Index: 5789648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3275. Min Act: -0.1700
Data Index: 6234600 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3275. Min Act: -0.1700
Data Index: 3977052 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3118. Min Act: -0.1700
Data Index: 3035936 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3275. Min Act: -0.1700
Data Index: 3898584 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3275. Min Act: -0.1700
Data Index: 7639948 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.3118. Min Act: -0.1700
Data Index: 6096605 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4686. Min Range: -3.4686
Max Act: 3.2961. Min Act: -0.1700
Data Index: 3774042 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19