Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.7672. Min Act: -0.1700
Data Index: 875514 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.7359. Min Act: -0.1700
Data Index: 5931088 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.6422. Min Act: -0.1700
Data Index: 6157739 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.5484. Min Act: -0.1700
Data Index: 988897 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.5172. Min Act: -0.1700
Data Index: 239704 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4859. Min Act: -0.1700
Data Index: 6177376 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4859. Min Act: -0.1700
Data Index: 8480247 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4859. Min Act: -0.1700
Data Index: 8653287 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4507739 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5359057 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4234. Min Act: -0.1700
Data Index: 5882312 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4234. Min Act: -0.1700
Data Index: 6503004 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4234. Min Act: -0.1700
Data Index: 8746238 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4234. Min Act: -0.1700
Data Index: 3623029 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4234. Min Act: -0.1700
Data Index: 8330867 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.4547. Min Act: -0.1700
Data Index: 8613869 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.3922. Min Act: -0.1700
Data Index: 2925835 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.3922. Min Act: -0.1700
Data Index: 4706037 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.3922. Min Act: -0.1700
Data Index: 2777470 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7672. Min Range: -5.7672
Max Act: 5.3922. Min Act: -0.1700
Data Index: 4364320 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19