Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.3348. Min Act: -0.1700
Data Index: 2820545 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.3191. Min Act: -0.1700
Data Index: 4365446 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.3034. Min Act: -0.1700
Data Index: 5609458 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2877. Min Act: -0.1700
Data Index: 5611735 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2563. Min Act: -0.1700
Data Index: 234465 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2563. Min Act: -0.1700
Data Index: 189626 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2406. Min Act: -0.1700
Data Index: 4744964 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2249. Min Act: -0.1700
Data Index: 6177278 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2406. Min Act: -0.1700
Data Index: 4744965 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6019250 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6133796 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6785537 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1934. Min Act: -0.1700
Data Index: 7869625 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1777. Min Act: -0.1700
Data Index: 3043681 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1934. Min Act: -0.1700
Data Index: 7417288 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1777. Min Act: -0.1700
Data Index: 664419 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1777. Min Act: -0.1700
Data Index: 1765142 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1620. Min Act: -0.1700
Data Index: 8524087 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1620. Min Act: -0.1700
Data Index: 4255251 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3348. Min Range: -3.3348
Max Act: 3.1305. Min Act: -0.1700
Data Index: 3854453 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19