Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.3021. Min Act: -0.1651
Data Index: 4871271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.3021. Min Act: -0.1700
Data Index: 866204 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.3021. Min Act: -0.1700
Data Index: 611961 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2864. Min Act: -0.1700
Data Index: 2117739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2864. Min Act: -0.1699
Data Index: 4871270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2550. Min Act: -0.1691
Data Index: 866203 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2550. Min Act: -0.1688
Data Index: 8383978 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2550. Min Act: -0.1700
Data Index: 1349762 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2393. Min Act: -0.1700
Data Index: 8246318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2393. Min Act: -0.1651
Data Index: 3586328 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2236. Min Act: -0.1651
Data Index: 4871262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2393. Min Act: -0.1691
Data Index: 687389 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2393. Min Act: -0.1700
Data Index: 687387 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2236. Min Act: -0.1700
Data Index: 6853411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2236. Min Act: -0.1699
Data Index: 4390940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2236. Min Act: -0.1700
Data Index: 3219505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2079. Min Act: -0.1699
Data Index: 4571991 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2079. Min Act: -0.1700
Data Index: 3586329 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2079. Min Act: -0.1700
Data Index: 5798624 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3021. Min Range: -3.3021
Max Act: 3.2079. Min Act: -0.1700
Data Index: 5640272 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19