Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.9717. Min Act: -0.1700
Data Index: 1942493 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.9404. Min Act: -0.1700
Data Index: 2178054 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.9092. Min Act: -0.1700
Data Index: 3069794 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7842. Min Act: -0.1700
Data Index: 4001845 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.8154. Min Act: -0.1700
Data Index: 1961802 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.8154. Min Act: -0.1700
Data Index: 6986510 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7529. Min Act: -0.1700
Data Index: 6847423 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7217. Min Act: -0.1700
Data Index: 2572837 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7217. Min Act: -0.1700
Data Index: 8242481 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7529. Min Act: -0.1700
Data Index: 7416781 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7217. Min Act: -0.1700
Data Index: 6440912 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7217. Min Act: -0.1700
Data Index: 2438891 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6904. Min Act: -0.1700
Data Index: 7310629 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.7217. Min Act: -0.1700
Data Index: 519739 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6904. Min Act: -0.1700
Data Index: 598989 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6592. Min Act: -0.1700
Data Index: 6281552 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6592. Min Act: -0.1700
Data Index: 4552957 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6279. Min Act: -0.1700
Data Index: 6641805 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6592. Min Act: -0.1700
Data Index: 2811791 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9717. Min Range: -6.9717
Max Act: 6.6592. Min Act: -0.1700
Data Index: 5655127 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19