Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.1931. Min Act: -0.1700
Data Index: 4664367 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.1459. Min Act: -0.1700
Data Index: 3533050 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.0356. Min Act: -0.1700
Data Index: 3742047 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.0513. Min Act: -0.1700
Data Index: 7788678 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.0040. Min Act: -0.1700
Data Index: 3657485 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.0198. Min Act: -0.1700
Data Index: 1211229 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1931. Min Range: -3.1931
Max Act: 3.0040. Min Act: -0.1700
Data Index: 1436157 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9723. Min Act: -0.1700
Data Index: 3145300 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9407. Min Act: -0.1700
Data Index: 5636145 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9565. Min Act: -0.1700
Data Index: 8160677 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9407. Min Act: -0.1700
Data Index: 2827585 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9249. Min Act: -0.1700
Data Index: 5810076 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9090. Min Act: -0.1700
Data Index: 8683874 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9090. Min Act: -0.1700
Data Index: 5146226 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.8931. Min Act: -0.1700
Data Index: 91032 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.9090. Min Act: -0.1700
Data Index: 2856284 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.8931. Min Act: -0.1700
Data Index: 419380 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.8931. Min Act: -0.1700
Data Index: 4157393 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.8773. Min Act: -0.1700
Data Index: 5676477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1931. Min Range: -3.1931
Max Act: 2.8931. Min Act: -0.1700
Data Index: 6075000 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19