Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4704. Min Act: -0.1700
Data Index: 1612148 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4704. Min Act: -0.1700
Data Index: 8000319 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4548. Min Act: -0.1700
Data Index: 6737971 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4234. Min Act: -0.1700
Data Index: 4032061 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4391. Min Act: -0.1700
Data Index: 6404386 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4077. Min Act: -0.1700
Data Index: 2475181 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4234. Min Act: -0.1700
Data Index: 2920021 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.4077. Min Act: -0.1700
Data Index: 1742215 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 7113455 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 2627265 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 567121 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 7612297 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 537041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 4284339 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 4945539 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 448217 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 5580312 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3764. Min Act: -0.1700
Data Index: 3010938 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3921. Min Act: -0.1700
Data Index: 3512019 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4704. Min Range: -3.4704
Max Act: 3.3607. Min Act: -0.1700
Data Index: 6175286 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19