Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 594 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.7776. Min Act: -0.1700
Data Index: 3022179 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.6994. Min Act: -0.1700
Data Index: 3022178 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.6681. Min Act: -0.1700
Data Index: 3667009 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.6368. Min Act: -0.1700
Data Index: 1990999 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.6212. Min Act: -0.1700
Data Index: 5469218 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.5899. Min Act: -0.1700
Data Index: 917885 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.5899. Min Act: -0.1700
Data Index: 7224352 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.5272. Min Act: -0.1700
Data Index: 947233 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.5116. Min Act: -0.1700
Data Index: 7097097 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4803. Min Act: -0.1700
Data Index: 2340670 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4803. Min Act: -0.1700
Data Index: 75372 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4959. Min Act: -0.1700
Data Index: 1880239 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4332. Min Act: -0.1700
Data Index: 2110416 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4176. Min Act: -0.1700
Data Index: 5352105 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4176. Min Act: -0.1700
Data Index: 4936706 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4019. Min Act: -0.1700
Data Index: 4433636 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4176. Min Act: -0.1700
Data Index: 7809959 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4176. Min Act: -0.1700
Data Index: 2165785 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.4019. Min Act: -0.1700
Data Index: 1954913 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7776. Min Range: -3.7776
Max Act: 3.3862. Min Act: -0.1700
Data Index: 3916710 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19