Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2247 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.7671. Min Act: -0.1700
Data Index: 6796286 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.7046. Min Act: -0.1700
Data Index: 6473168 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.6734. Min Act: -0.1700
Data Index: 1609221 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.6734. Min Act: -0.1700
Data Index: 8688449 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.6421. Min Act: -0.1700
Data Index: 210793 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.6109. Min Act: -0.1700
Data Index: 3473088 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.5796. Min Act: -0.1700
Data Index: 8755095 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.5796. Min Act: -0.1700
Data Index: 482329 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.5171. Min Act: -0.1700
Data Index: 4169424 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.5171. Min Act: -0.1700
Data Index: 6250591 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4859. Min Act: -0.1700
Data Index: 2523719 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.5484. Min Act: -0.1700
Data Index: 8688450 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4859. Min Act: -0.1700
Data Index: 2071179 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4859. Min Act: -0.1700
Data Index: 8023371 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4859. Min Act: -0.1700
Data Index: 4047648 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4859. Min Act: -0.1700
Data Index: 2071177 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4546. Min Act: -0.1700
Data Index: 6210219 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4546. Min Act: -0.1700
Data Index: 1984739 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4546. Min Act: -0.1700
Data Index: 1422138 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7671. Min Range: -4.7671
Max Act: 4.4234. Min Act: -0.1700
Data Index: 6210217 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19