Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2418 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1608. Min Range: -4.1608
Max Act: 4.1608. Min Act: -0.1700
Data Index: 247126 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.9107. Min Act: -0.1700
Data Index: 2804220 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.8638. Min Act: -0.1700
Data Index: 8561736 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.8794. Min Act: -0.1700
Data Index: 8060398 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.8169. Min Act: -0.1700
Data Index: 1001079 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7700. Min Act: -0.1700
Data Index: 6885071 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7543. Min Act: -0.1700
Data Index: 8743433 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7700. Min Act: -0.1700
Data Index: 4832967 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7856. Min Act: -0.1700
Data Index: 6629895 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7543. Min Act: -0.1700
Data Index: 3692044 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7700. Min Act: -0.1700
Data Index: 501993 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7700. Min Act: -0.1700
Data Index: 4473327 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7387. Min Act: -0.1700
Data Index: 268283 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7387. Min Act: -0.1700
Data Index: 4771425 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7387. Min Act: -0.1700
Data Index: 5707868 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7231. Min Act: -0.1700
Data Index: 2551914 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7231. Min Act: -0.1700
Data Index: 6139153 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7074. Min Act: -0.1700
Data Index: 4811121 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7074. Min Act: -0.1700
Data Index: 2487786 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1608. Min Range: -4.1608
Max Act: 3.7074. Min Act: -0.1700
Data Index: 5807058 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19