Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5982. Min Act: -0.1700
Data Index: 5684215 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5669. Min Act: -0.1700
Data Index: 1693312 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5044. Min Act: -0.1700
Data Index: 3300008 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5044. Min Act: -0.1700
Data Index: 5644624 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.4419. Min Act: -0.1700
Data Index: 5091850 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.4732. Min Act: -0.1700
Data Index: 1278447 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.4732. Min Act: -0.1700
Data Index: 1884843 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.4419. Min Act: -0.1700
Data Index: 7719359 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3794. Min Act: -0.1700
Data Index: 2724161 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3794. Min Act: -0.1700
Data Index: 2941752 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3482. Min Act: -0.1700
Data Index: 1664669 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3482. Min Act: -0.1700
Data Index: 1854904 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3482. Min Act: -0.1700
Data Index: 6905402 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3169. Min Act: -0.1700
Data Index: 8119 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3169. Min Act: -0.1700
Data Index: 5247064 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3676321 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2857. Min Act: -0.1700
Data Index: 7441944 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2857. Min Act: -0.1700
Data Index: 108689 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2544. Min Act: -0.1700
Data Index: 8270767 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2544. Min Act: -0.1700
Data Index: 6955268 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19