Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0648. Min Range: -5.0648
Max Act: 5.0648. Min Act: -0.1700
Data Index: 2584887 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.8460. Min Act: -0.1700
Data Index: 6797116 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.7835. Min Act: -0.1700
Data Index: 805308 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.7210. Min Act: -0.1700
Data Index: 5150824 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5922773 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5538153 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.6898. Min Act: -0.1700
Data Index: 3889947 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.6585. Min Act: -0.1700
Data Index: 7875546 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.6585. Min Act: -0.1700
Data Index: 6639536 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5960. Min Act: -0.1700
Data Index: 7315005 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5960. Min Act: -0.1700
Data Index: 4638411 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5960. Min Act: -0.1700
Data Index: 4396277 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5648. Min Act: -0.1700
Data Index: 7370506 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5648. Min Act: -0.1700
Data Index: 8171222 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5648. Min Act: -0.1700
Data Index: 5817528 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5335. Min Act: -0.1700
Data Index: 5292341 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5335. Min Act: -0.1700
Data Index: 811643 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5335. Min Act: -0.1700
Data Index: 4573923 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5335. Min Act: -0.1700
Data Index: 3481000 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0648. Min Range: -5.0648
Max Act: 4.5335. Min Act: -0.1700
Data Index: 1144362 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19