Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.8916. Min Act: -0.1700
Data Index: 1321810 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4853. Min Act: -0.1700
Data Index: 8212073 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4541. Min Act: -0.1700
Data Index: 7723959 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4541. Min Act: -0.1700
Data Index: 5111267 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4228. Min Act: -0.1700
Data Index: 4635681 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4228. Min Act: -0.1700
Data Index: 4813553 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.4228. Min Act: -0.1700
Data Index: 5224601 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3603. Min Act: -0.1700
Data Index: 7600149 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3603. Min Act: -0.1700
Data Index: 3508543 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3291. Min Act: -0.1700
Data Index: 206626 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3291. Min Act: -0.1700
Data Index: 3963408 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.3291. Min Act: -0.1700
Data Index: 6848233 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 1015449 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 2644092 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 4185989 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 2534753 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 1658148 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 746203 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2978. Min Act: -0.1700
Data Index: 7197041 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8916. Min Range: -5.8916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 6731704 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19