Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.5109. Min Act: -0.1700
Data Index: 875156 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.5109. Min Act: -0.1700
Data Index: 8001349 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.4796. Min Act: -0.1700
Data Index: 2624448 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.4171. Min Act: -0.1700
Data Index: 2624443 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.4796. Min Act: -0.1700
Data Index: 1542518 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2921. Min Act: -0.1700
Data Index: 7832781 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.3234. Min Act: -0.1700
Data Index: 1371252 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2921. Min Act: -0.1700
Data Index: 7450889 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2609. Min Act: -0.1700
Data Index: 6198513 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2609. Min Act: -0.1700
Data Index: 5395949 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2609. Min Act: -0.1700
Data Index: 6979333 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2296. Min Act: -0.1700
Data Index: 3909601 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.2296. Min Act: -0.1700
Data Index: 7327213 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1671. Min Act: -0.1700
Data Index: 2319400 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1671. Min Act: -0.1700
Data Index: 5712543 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1671. Min Act: -0.1700
Data Index: 5937798 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1984. Min Act: -0.1700
Data Index: 7578540 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1359. Min Act: -0.1700
Data Index: 6571004 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1671. Min Act: -0.1700
Data Index: 5154086 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5109. Min Range: -5.5109
Max Act: 5.1671. Min Act: -0.1700
Data Index: 5636665 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19