Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9856. Min Act: -0.1700
Data Index: 7600350 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9856. Min Act: -0.1700
Data Index: 5513120 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9544. Min Act: -0.1700
Data Index: 5218635 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 8321580 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 218414 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 1307964 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 811263 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 6232019 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9544. Min Act: -0.1700
Data Index: 6414241 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 6414242 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.9231. Min Act: -0.1700
Data Index: 3245905 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8606. Min Act: -0.1700
Data Index: 7377426 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 3621747 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 7332394 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 2632682 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 7326407 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 7314207 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 6304264 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 5886448 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9856. Min Range: -4.9856
Max Act: 4.8919. Min Act: -0.1700
Data Index: 4137984 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19