Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0331. Min Range: -6.0331
Max Act: 6.0331. Min Act: -0.1700
Data Index: 6906050 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.9394. Min Act: -0.1700
Data Index: 6106805 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.9081. Min Act: -0.1700
Data Index: 2847549 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.9081. Min Act: -0.1700
Data Index: 2184396 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.9081. Min Act: -0.1700
Data Index: 5572208 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.9081. Min Act: -0.1700
Data Index: 4142439 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 458808 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 7103198 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 2184344 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 1784243 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 2239535 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2758283 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 3323194 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2764174 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 1110161 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4627227 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4503440 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6408245 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2617628 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0331. Min Range: -6.0331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 1307014 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19