Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 166 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.9480. Min Act: -0.1700
Data Index: 6103582 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.9480. Min Act: -0.1700
Data Index: 559597 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.8230. Min Act: -0.1700
Data Index: 7972343 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.8855. Min Act: -0.1700
Data Index: 8461809 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.6980. Min Act: -0.1700
Data Index: 4339539 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.6980. Min Act: -0.1700
Data Index: 7293069 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.6980. Min Act: -0.1700
Data Index: 4740016 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.5730. Min Act: -0.1700
Data Index: 4339541 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.5105. Min Act: -0.1700
Data Index: 6244797 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.5105. Min Act: -0.1700
Data Index: 7972341 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.5105. Min Act: -0.1700
Data Index: 7805965 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.4480. Min Act: -0.1700
Data Index: 4438656 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.3230. Min Act: -0.1700
Data Index: 1663134 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.3855. Min Act: -0.1700
Data Index: 6020215 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.3855. Min Act: -0.1700
Data Index: 8461807 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.3230. Min Act: -0.1700
Data Index: 5439751 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.2605. Min Act: -0.1700
Data Index: 5095291 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.2605. Min Act: -0.1700
Data Index: 5239792 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.2605. Min Act: -0.1700
Data Index: 4576541 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9480. Min Range: -9.9480
Max Act: 9.2605. Min Act: -0.1700
Data Index: 4645845 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19