Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1179 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1554. Min Range: -5.1554
Max Act: 5.1554. Min Act: -0.1700
Data Index: 5508724 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.9367. Min Act: -0.1700
Data Index: 8210401 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.9367. Min Act: -0.1700
Data Index: 1010367 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.9054. Min Act: -0.1700
Data Index: 8746154 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.9054. Min Act: -0.1700
Data Index: 6382191 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8742. Min Act: -0.1700
Data Index: 1952498 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8742. Min Act: -0.1700
Data Index: 3413871 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.9054. Min Act: -0.1700
Data Index: 5242371 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8742. Min Act: -0.1700
Data Index: 6930842 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8742. Min Act: -0.1700
Data Index: 5667902 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8117. Min Act: -0.1700
Data Index: 6400295 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8117. Min Act: -0.1700
Data Index: 4756406 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8429. Min Act: -0.1700
Data Index: 7380079 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7804. Min Act: -0.1700
Data Index: 3744224 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7804. Min Act: -0.1700
Data Index: 6269902 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.8429. Min Act: -0.1700
Data Index: 8030143 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7804. Min Act: -0.1700
Data Index: 3559245 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7804. Min Act: -0.1700
Data Index: 5214719 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7492. Min Act: -0.1700
Data Index: 961657 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1554. Min Range: -5.1554
Max Act: 4.7492. Min Act: -0.1700
Data Index: 7596064 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19