Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.4693. Min Act: -0.1700
Data Index: 4384088 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.4341. Min Act: -0.1700
Data Index: 7053392 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3989. Min Act: -0.1700
Data Index: 7445901 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3989. Min Act: -0.1700
Data Index: 1643281 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3636. Min Act: -0.1700
Data Index: 6102804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3460. Min Act: -0.1700
Data Index: 5301187 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3283. Min Act: -0.1699
Data Index: 6147772 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3107. Min Act: -0.1700
Data Index: 2478152 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3283. Min Act: -0.1700
Data Index: 2323685 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3107. Min Act: -0.1700
Data Index: 5301178 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.3107. Min Act: -0.1699
Data Index: 5594926 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2931. Min Act: -0.1700
Data Index: 4845875 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2931. Min Act: -0.1700
Data Index: 2565455 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2931. Min Act: -0.1694
Data Index: 5124115 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2754. Min Act: -0.1700
Data Index: 5015138 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2578. Min Act: -0.1700
Data Index: 6618794 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2402. Min Act: -0.1700
Data Index: 5737261 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2578. Min Act: -0.1700
Data Index: 7275706 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2402. Min Act: -0.1700
Data Index: 7362420 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4693. Min Range: -1.4693
Max Act: 1.2578. Min Act: -0.1698
Data Index: 5301188 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19