Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.6976. Min Act: -0.1700
Data Index: 7870084 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.6037. Min Act: -0.1700
Data Index: 8618161 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5881. Min Act: -0.1700
Data Index: 8726254 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5568. Min Act: -0.1700
Data Index: 8756018 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5568. Min Act: -0.1700
Data Index: 1286452 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5411. Min Act: -0.1700
Data Index: 188961 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5568. Min Act: -0.1700
Data Index: 191527 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5411. Min Act: -0.1700
Data Index: 8145159 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5411. Min Act: -0.1700
Data Index: 1990992 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5098. Min Act: -0.1700
Data Index: 7513569 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4941. Min Act: -0.1700
Data Index: 8754177 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4941. Min Act: -0.1700
Data Index: 1285885 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5098. Min Act: -0.1700
Data Index: 8777850 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.5098. Min Act: -0.1700
Data Index: 2112860 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4784. Min Act: -0.1700
Data Index: 4305889 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4628. Min Act: -0.1700
Data Index: 2957714 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4471. Min Act: -0.1700
Data Index: 4724935 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4471. Min Act: -0.1700
Data Index: 3940192 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4314. Min Act: -0.1700
Data Index: 2291385 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6976. Min Range: -3.6976
Max Act: 3.4158. Min Act: -0.1700
Data Index: 5664385 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19