Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.1167. Min Act: -0.1700
Data Index: 4238575 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.1010. Min Act: -0.1700
Data Index: 8827613 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0852. Min Act: -0.1700
Data Index: 2570875 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0852. Min Act: -0.1700
Data Index: 31359 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0536. Min Act: -0.1700
Data Index: 6376334 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0379. Min Act: -0.1700
Data Index: 5517614 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0379. Min Act: -0.1700
Data Index: 3746874 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0379. Min Act: -0.1700
Data Index: 8357326 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0536. Min Act: -0.1700
Data Index: 8461823 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0379. Min Act: -0.1700
Data Index: 5064708 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1167. Min Range: -3.1167
Max Act: 3.0063. Min Act: -0.1700
Data Index: 1709623 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9747. Min Act: -0.1700
Data Index: 5611359 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9905. Min Act: -0.1700
Data Index: 3175591 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9588. Min Act: -0.1700
Data Index: 891767 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9747. Min Act: -0.1700
Data Index: 4544115 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9747. Min Act: -0.1700
Data Index: 3320578 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9747. Min Act: -0.1700
Data Index: 6397954 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9430. Min Act: -0.1700
Data Index: 6746295 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9588. Min Act: -0.1700
Data Index: 1516161 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1167. Min Range: -3.1167
Max Act: 2.9272. Min Act: -0.1700
Data Index: 425749 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19