Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1469 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.7664. Min Act: -0.1700
Data Index: 7142629 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.7038. Min Act: -0.1700
Data Index: 544254 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.6256. Min Act: -0.1700
Data Index: 5778141 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5473. Min Act: -0.1700
Data Index: 5924383 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5473. Min Act: -0.1700
Data Index: 3600189 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5473. Min Act: -0.1700
Data Index: 7016790 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5473. Min Act: -0.1700
Data Index: 5090115 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5004. Min Act: -0.1700
Data Index: 4095480 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.5004. Min Act: -0.1700
Data Index: 2402617 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4847. Min Act: -0.1700
Data Index: 2647527 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4690. Min Act: -0.1700
Data Index: 7969046 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4690. Min Act: -0.1700
Data Index: 1490568 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4220. Min Act: -0.1700
Data Index: 3128566 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4377. Min Act: -0.1700
Data Index: 459191 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4220. Min Act: -0.1700
Data Index: 4317316 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4377. Min Act: -0.1700
Data Index: 3369092 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4220. Min Act: -0.1700
Data Index: 254640 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.3907. Min Act: -0.1700
Data Index: 1008636 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.4063. Min Act: -0.1700
Data Index: 7780832 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7664. Min Range: -3.7664
Max Act: 3.3750. Min Act: -0.1700
Data Index: 732971 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19