Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.9171. Min Act: -0.1700
Data Index: 7626266 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.8546. Min Act: -0.1700
Data Index: 7075044 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.7296. Min Act: -0.1700
Data Index: 7148125 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6277688 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.6671. Min Act: -0.1700
Data Index: 3695270 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.6359. Min Act: -0.1700
Data Index: 8362331 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.6046. Min Act: -0.1700
Data Index: 1873334 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5421. Min Act: -0.1700
Data Index: 7912005 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5734. Min Act: -0.1700
Data Index: 1714171 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5421. Min Act: -0.1700
Data Index: 26387 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6187747 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5421. Min Act: -0.1700
Data Index: 8003433 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5109. Min Act: -0.1700
Data Index: 1756096 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.5109. Min Act: -0.1700
Data Index: 2113232 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4796. Min Act: -0.1700
Data Index: 1859094 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4796. Min Act: -0.1700
Data Index: 754702 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4796. Min Act: -0.1700
Data Index: 8105934 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4796. Min Act: -0.1700
Data Index: 264565 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4796. Min Act: -0.1700
Data Index: 4314997 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9171. Min Range: -5.9171
Max Act: 5.4484. Min Act: -0.1700
Data Index: 3030076 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19