Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.3118. Min Act: -0.1700
Data Index: 1444011 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.2805. Min Act: -0.1700
Data Index: 6270384 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.2805. Min Act: -0.1700
Data Index: 1498105 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.1555. Min Act: -0.1700
Data Index: 2413645 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.1555. Min Act: -0.1700
Data Index: 5073852 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.1243. Min Act: -0.1700
Data Index: 4809438 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.1243. Min Act: -0.1700
Data Index: 8030170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.0930. Min Act: -0.1700
Data Index: 4137432 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.0618. Min Act: -0.1700
Data Index: 2649003 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.0305. Min Act: -0.1700
Data Index: 8688979 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.0618. Min Act: -0.1700
Data Index: 3737371 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3118. Min Range: -5.3118
Max Act: 5.0305. Min Act: -0.1700
Data Index: 8464414 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5815878 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8801278 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9680. Min Act: -0.1700
Data Index: 5423812 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9368. Min Act: -0.1700
Data Index: 1786345 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9368. Min Act: -0.1700
Data Index: 6913088 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3027173 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2021294 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3118. Min Range: -5.3118
Max Act: 4.9055. Min Act: -0.1700
Data Index: 672266 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19