Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1752 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.9545. Min Act: -0.1700
Data Index: 6256214 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.8920. Min Act: -0.1700
Data Index: 5862146 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.7670. Min Act: -0.1700
Data Index: 4930211 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.7670. Min Act: -0.1700
Data Index: 2982930 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.7045. Min Act: -0.1700
Data Index: 4589535 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.7045. Min Act: -0.1700
Data Index: 5697453 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.7045. Min Act: -0.1700
Data Index: 5841862 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.6420. Min Act: -0.1700
Data Index: 4243049 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.6420. Min Act: -0.1700
Data Index: 8286881 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.6420. Min Act: -0.1700
Data Index: 7051674 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.5795. Min Act: -0.1700
Data Index: 3400955 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.5170. Min Act: -0.1700
Data Index: 7726881 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.5170. Min Act: -0.1700
Data Index: 1901010 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.4545. Min Act: -0.1700
Data Index: 4569260 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.4545. Min Act: -0.1700
Data Index: 83773 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.4545. Min Act: -0.1700
Data Index: 3939237 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.3920. Min Act: -0.1700
Data Index: 1050679 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.3920. Min Act: -0.1700
Data Index: 4400652 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.3920. Min Act: -0.1700
Data Index: 8428647 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9545. Min Range: -10.9545
Max Act: 10.3295. Min Act: -0.1700
Data Index: 7059101 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19