Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1447. Min Range: -8.1447
Max Act: 8.1447. Min Act: -0.1700
Data Index: 2178040 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.9572. Min Act: -0.1700
Data Index: 2476484 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.8635. Min Act: -0.1700
Data Index: 7343577 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.8322. Min Act: -0.1700
Data Index: 6043055 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.6447. Min Act: -0.1700
Data Index: 2355702 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.6447. Min Act: -0.1700
Data Index: 4030476 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.6135. Min Act: -0.1700
Data Index: 3809353 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.5822. Min Act: -0.1700
Data Index: 1562922 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.5197. Min Act: -0.1700
Data Index: 1057302 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.5197. Min Act: -0.1700
Data Index: 3376720 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.5197. Min Act: -0.1700
Data Index: 1317771 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4885. Min Act: -0.1700
Data Index: 6692562 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4885. Min Act: -0.1700
Data Index: 480548 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4885. Min Act: -0.1700
Data Index: 6010341 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5639085 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4260. Min Act: -0.1700
Data Index: 7529067 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4260. Min Act: -0.1700
Data Index: 6440821 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.3947. Min Act: -0.1700
Data Index: 3790077 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4260. Min Act: -0.1700
Data Index: 8189848 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4260. Min Act: -0.1700
Data Index: 7017644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19