Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.9672. Min Act: -0.1700
Data Index: 4044347 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.8422. Min Act: -0.1700
Data Index: 4820902 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.7484. Min Act: -0.1700
Data Index: 3292453 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.7172. Min Act: -0.1700
Data Index: 2295293 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.6859. Min Act: -0.1700
Data Index: 8814688 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.6547. Min Act: -0.1700
Data Index: 3271385 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.6234. Min Act: -0.1700
Data Index: 3927396 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5922. Min Act: -0.1700
Data Index: 4323076 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.6234. Min Act: -0.1700
Data Index: 7413047 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.6234. Min Act: -0.1700
Data Index: 5652400 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5922. Min Act: -0.1700
Data Index: 294356 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5922. Min Act: -0.1700
Data Index: 2531958 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5922. Min Act: -0.1700
Data Index: 1845838 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5922. Min Act: -0.1700
Data Index: 5220658 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5609. Min Act: -0.1700
Data Index: 6020402 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5609. Min Act: -0.1700
Data Index: 4109701 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5609. Min Act: -0.1700
Data Index: 1254480 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5297. Min Act: -0.1700
Data Index: 2037170 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5609. Min Act: -0.1700
Data Index: 2237368 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9672. Min Range: -6.9672
Max Act: 6.5297. Min Act: -0.1700
Data Index: 7554716 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19