Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8993. Min Act: -0.1700
Data Index: 148886 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8368. Min Act: -0.1700
Data Index: 4387660 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7898. Min Act: -0.1700
Data Index: 6623050 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7429. Min Act: -0.1700
Data Index: 3560240 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 8137973 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 7376388 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 2638035 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6647. Min Act: -0.1700
Data Index: 3530169 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6647. Min Act: -0.1700
Data Index: 37987 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6334. Min Act: -0.1700
Data Index: 3752169 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6021. Min Act: -0.1700
Data Index: 8565794 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6178. Min Act: -0.1700
Data Index: 2699731 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6178. Min Act: -0.1700
Data Index: 4801950 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6021. Min Act: -0.1700
Data Index: 2461120 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5865. Min Act: -0.1700
Data Index: 6861949 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5865. Min Act: -0.1700
Data Index: 2060135 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5708. Min Act: -0.1700
Data Index: 6072166 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5708. Min Act: -0.1700
Data Index: 1201752 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5708. Min Act: -0.1700
Data Index: 5513817 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.5708. Min Act: -0.1700
Data Index: 7579381 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19