Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.9010. Min Act: -0.1700
Data Index: 6166316 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6822. Min Act: -0.1700
Data Index: 6783733 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6510. Min Act: -0.1700
Data Index: 5713932 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.6197. Min Act: -0.1700
Data Index: 4466184 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.5885. Min Act: -0.1700
Data Index: 1368772 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.5572. Min Act: -0.1700
Data Index: 4460486 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.5260. Min Act: -0.1700
Data Index: 8351217 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4147534 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3083304 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4634716 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4322. Min Act: -0.1700
Data Index: 2042044 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4635. Min Act: -0.1700
Data Index: 4677510 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4322. Min Act: -0.1700
Data Index: 4394158 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4322. Min Act: -0.1700
Data Index: 2380601 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4010. Min Act: -0.1700
Data Index: 2743125 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4010. Min Act: -0.1700
Data Index: 8400290 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.4010. Min Act: -0.1700
Data Index: 4370346 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.3697. Min Act: -0.1700
Data Index: 7355546 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.3697. Min Act: -0.1700
Data Index: 2831277 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9010. Min Range: -4.9010
Max Act: 4.3697. Min Act: -0.1700
Data Index: 1628182 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19