Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.5330. Min Act: -0.1700
Data Index: 813365 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.5642. Min Act: -0.1700
Data Index: 5220013 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.4705. Min Act: -0.1700
Data Index: 8148121 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.4080. Min Act: -0.1700
Data Index: 6291559 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.4080. Min Act: -0.1700
Data Index: 666394 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.3455. Min Act: -0.1700
Data Index: 7426768 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.3142. Min Act: -0.1700
Data Index: 6865757 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1283937 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2830. Min Act: -0.1700
Data Index: 5611161 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2830. Min Act: -0.1700
Data Index: 4572381 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1849895 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2517. Min Act: -0.1700
Data Index: 488471 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2517. Min Act: -0.1700
Data Index: 8140837 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2517. Min Act: -0.1700
Data Index: 3617172 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2205. Min Act: -0.1700
Data Index: 6024609 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2517. Min Act: -0.1700
Data Index: 2172947 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.2205. Min Act: -0.1700
Data Index: 181909 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.1892. Min Act: -0.1700
Data Index: 5427003 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.1580. Min Act: -0.1700
Data Index: 6679343 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5642. Min Range: -4.5642
Max Act: 4.1580. Min Act: -0.1700
Data Index: 5226952 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19