Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4137 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.2205. Min Act: -0.1700
Data Index: 7893651 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0643. Min Act: -0.1700
Data Index: 4731147 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0643. Min Act: -0.1700
Data Index: 8479358 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0330. Min Act: -0.1700
Data Index: 4481137 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 1055024 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 2877794 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.0018. Min Act: -0.1700
Data Index: 5801675 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9705. Min Act: -0.1700
Data Index: 5082859 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9080. Min Act: -0.1700
Data Index: 7037763 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 2881690 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9080. Min Act: -0.1700
Data Index: 865935 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 1362910 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 896289 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 4914641 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 6655709 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 8060804 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 4691954 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 677637 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 2026655 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 7690087 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19