Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.6707. Min Act: -0.1700
Data Index: 4618895 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.2633. Min Act: -0.1700
Data Index: 7586103 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.1375. Min Act: -0.1700
Data Index: 3653667 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.1532. Min Act: -0.1700
Data Index: 7705137 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.1060. Min Act: -0.1700
Data Index: 8485141 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.0587. Min Act: -0.1700
Data Index: 8238874 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.0113. Min Act: -0.1700
Data Index: 1857203 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9955. Min Act: -0.1700
Data Index: 2221646 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6707. Min Range: -3.6707
Max Act: 3.0113. Min Act: -0.1700
Data Index: 6069987 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9797. Min Act: -0.1700
Data Index: 5010198 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9955. Min Act: -0.1700
Data Index: 5906994 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9639. Min Act: -0.1700
Data Index: 1103750 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9797. Min Act: -0.1700
Data Index: 5968322 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9164. Min Act: -0.1700
Data Index: 8642089 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9005. Min Act: -0.1700
Data Index: 377179 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9322. Min Act: -0.1700
Data Index: 5965570 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.9164. Min Act: -0.1700
Data Index: 2784767 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.8846. Min Act: -0.1700
Data Index: 2690759 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.8688. Min Act: -0.1700
Data Index: 6293420 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6707. Min Range: -3.6707
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2489278 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19