Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4639. Min Act: -0.1700
Data Index: 748395 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4419. Min Act: -0.1700
Data Index: 2964263 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4347. Min Act: -0.1700
Data Index: 1812175 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4347. Min Act: -0.1700
Data Index: 8404203 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4275. Min Act: -0.1700
Data Index: 1812177 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4203. Min Act: -0.1698
Data Index: 1262450 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4132. Min Act: -0.1700
Data Index: 8635029 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4203. Min Act: -0.1700
Data Index: 2100883 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.4060. Min Act: -0.1700
Data Index: 5988554 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3990. Min Act: -0.1700
Data Index: 8648116 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3990. Min Act: -0.1700
Data Index: 1685638 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3990. Min Act: -0.1700
Data Index: 7639143 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3780. Min Act: -0.1700
Data Index: 7551315 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3780. Min Act: -0.1700
Data Index: 1305177 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3710. Min Act: -0.1700
Data Index: 8606435 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3641. Min Act: -0.1700
Data Index: 3707806 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3641. Min Act: -0.1700
Data Index: 6891777 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3641. Min Act: -0.1700
Data Index: 325793 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3641. Min Act: -0.1700
Data Index: 6454569 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4639. Min Range: -0.4639
Max Act: 0.3573. Min Act: -0.1700
Data Index: 2270674 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19