Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.8032. Min Act: -0.1700
Data Index: 2663834 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.7407. Min Act: -0.1700
Data Index: 2924503 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 4870534 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5532. Min Act: -0.1700
Data Index: 2924504 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5532. Min Act: -0.1700
Data Index: 5182541 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5532. Min Act: -0.1700
Data Index: 1876612 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 5226682 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 915953 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 1586619 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 4660294 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 4441547 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 8807747 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5220. Min Act: -0.1700
Data Index: 192869 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2242702 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 7817230 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 8255500 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2372711 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4595. Min Act: -0.1700
Data Index: 1124251 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4282. Min Act: -0.1700
Data Index: 3487184 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4282. Min Act: -0.1700
Data Index: 3665708 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19