Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.4837. Min Act: -0.1700
Data Index: 5613991 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.3587. Min Act: -0.1700
Data Index: 988369 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.3274. Min Act: -0.1700
Data Index: 8526074 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.3274. Min Act: -0.1700
Data Index: 6133600 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.2024. Min Act: -0.1700
Data Index: 5976238 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.2024. Min Act: -0.1700
Data Index: 2290718 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.2024. Min Act: -0.1700
Data Index: 244877 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.1712. Min Act: -0.1700
Data Index: 2451031 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.1399. Min Act: -0.1700
Data Index: 6625332 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.1087. Min Act: -0.1700
Data Index: 2835689 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.1087. Min Act: -0.1700
Data Index: 1249468 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 8588732 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 2691682 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 6115190 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 4922772 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 761076 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0774. Min Act: -0.1700
Data Index: 5624832 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0462. Min Act: -0.1700
Data Index: 6071304 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0462. Min Act: -0.1700
Data Index: 3390884 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4837. Min Range: -5.4837
Max Act: 5.0149. Min Act: -0.1700
Data Index: 6393719 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19