Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.3708. Min Act: -0.1700
Data Index: 4213929 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.2770. Min Act: -0.1700
Data Index: 7717267 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.2145. Min Act: -0.1700
Data Index: 8364505 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.2145. Min Act: -0.1700
Data Index: 8145421 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1832. Min Act: -0.1700
Data Index: 3000692 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.2145. Min Act: -0.1700
Data Index: 3752118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1520. Min Act: -0.1700
Data Index: 4589434 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1832. Min Act: -0.1700
Data Index: 7961191 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1207. Min Act: -0.1700
Data Index: 7521703 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1207. Min Act: -0.1700
Data Index: 2615327 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.1207. Min Act: -0.1700
Data Index: 6258439 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 8145420 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 7736196 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0895. Min Act: -0.1700
Data Index: 1577697 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0582. Min Act: -0.1700
Data Index: 4316845 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0582. Min Act: -0.1700
Data Index: 1155401 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0270. Min Act: -0.1700
Data Index: 8117853 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0270. Min Act: -0.1700
Data Index: 5949760 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0270. Min Act: -0.1700
Data Index: 6951543 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3708. Min Range: -4.3708
Max Act: 4.0270. Min Act: -0.1700
Data Index: 6993038 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19