Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8831. Min Act: -0.1700
Data Index: 1365460 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8831. Min Act: -0.1700
Data Index: 4773795 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8831. Min Act: -0.1700
Data Index: 7703688 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8518. Min Act: -0.1700
Data Index: 7011556 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8518. Min Act: -0.1700
Data Index: 7255789 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8205. Min Act: -0.1700
Data Index: 6016637 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8205. Min Act: -0.1700
Data Index: 8410630 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.8205. Min Act: -0.1700
Data Index: 8158279 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7893. Min Act: -0.1700
Data Index: 8056024 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7893. Min Act: -0.1700
Data Index: 6347626 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7893. Min Act: -0.1700
Data Index: 1836852 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7580. Min Act: -0.1700
Data Index: 2696442 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7580. Min Act: -0.1700
Data Index: 6194186 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 2623977 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6954. Min Act: -0.1700
Data Index: 4919771 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 5062356 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6954. Min Act: -0.1700
Data Index: 3406409 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.7267. Min Act: -0.1700
Data Index: 4096384 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6954. Min Act: -0.1700
Data Index: 2843501 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8831. Min Range: -3.8831
Max Act: 3.6641. Min Act: -0.1700
Data Index: 3231831 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19