Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.2728. Min Act: -0.1700
Data Index: 4494004 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.2416. Min Act: -0.1700
Data Index: 822120 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.2103. Min Act: -0.1700
Data Index: 4927283 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.1791. Min Act: -0.1700
Data Index: 2193890 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.1478. Min Act: -0.1700
Data Index: 2900028 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.1478. Min Act: -0.1700
Data Index: 8249692 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.0853. Min Act: -0.1700
Data Index: 1156062 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2728. Min Range: -6.2728
Max Act: 6.0541. Min Act: -0.1700
Data Index: 7000301 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9916. Min Act: -0.1700
Data Index: 571975 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1568729 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9916. Min Act: -0.1700
Data Index: 3867349 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9916. Min Act: -0.1700
Data Index: 3579277 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9291. Min Act: -0.1700
Data Index: 4908249 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8372664 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.9603. Min Act: -0.1700
Data Index: 8414795 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.8978. Min Act: -0.1700
Data Index: 89857 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.8978. Min Act: -0.1700
Data Index: 6156681 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.8353. Min Act: -0.1700
Data Index: 6535500 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.8666. Min Act: -0.1700
Data Index: 5957453 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2728. Min Range: -6.2728
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1539471 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19