Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.7567. Min Act: -0.1700
Data Index: 7196629 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.7254. Min Act: -0.1700
Data Index: 5196074 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.5533. Min Act: -0.1700
Data Index: 2457767 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.5220. Min Act: -0.1700
Data Index: 1724182 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4907. Min Act: -0.1700
Data Index: 5643158 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.5063. Min Act: -0.1700
Data Index: 7685838 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4907. Min Act: -0.1700
Data Index: 160644 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4750. Min Act: -0.1700
Data Index: 2144988 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4750. Min Act: -0.1700
Data Index: 930097 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4750. Min Act: -0.1700
Data Index: 3909539 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4593. Min Act: -0.1700
Data Index: 8811268 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4593. Min Act: -0.1700
Data Index: 605552 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4437. Min Act: -0.1700
Data Index: 5118172 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4437. Min Act: -0.1700
Data Index: 5863000 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4593. Min Act: -0.1700
Data Index: 6361117 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4437. Min Act: -0.1700
Data Index: 1627914 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4437. Min Act: -0.1700
Data Index: 3721226 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4280. Min Act: -0.1700
Data Index: 1205243 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4280. Min Act: -0.1700
Data Index: 4752068 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7567. Min Range: -3.7567
Max Act: 3.4280. Min Act: -0.1700
Data Index: 1938478 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19