Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7586. Min Act: -0.1700
Data Index: 1484447 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7586. Min Act: -0.1700
Data Index: 1230376 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7274. Min Act: -0.1700
Data Index: 1614165 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7586. Min Act: -0.1700
Data Index: 158122 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 8479167 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 574222 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 3908524 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 7488515 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 1775927 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 5370685 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5370670 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 4836461 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 4265624 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5626093 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6649. Min Act: -0.1700
Data Index: 1650957 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 527628 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1263670 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 2089665 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 5370687 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 4525033 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19