Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2844. Min Range: -8.2844
Max Act: 8.2844. Min Act: -0.1700
Data Index: 2335788 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.9094. Min Act: -0.1700
Data Index: 152597 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.9094. Min Act: -0.1700
Data Index: 669445 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5969. Min Act: -0.1700
Data Index: 7054259 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5969. Min Act: -0.1700
Data Index: 1022983 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5657. Min Act: -0.1700
Data Index: 5917358 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5969. Min Act: -0.1700
Data Index: 2869959 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5344. Min Act: -0.1700
Data Index: 4374068 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5032. Min Act: -0.1700
Data Index: 4369385 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.5032. Min Act: -0.1700
Data Index: 2691752 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.4407. Min Act: -0.1700
Data Index: 4171403 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.4407. Min Act: -0.1700
Data Index: 912543 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.4407. Min Act: -0.1700
Data Index: 5722527 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.4094. Min Act: -0.1700
Data Index: 3231415 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.4094. Min Act: -0.1700
Data Index: 2592431 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.3782. Min Act: -0.1700
Data Index: 2825200 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.3782. Min Act: -0.1700
Data Index: 3863522 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.3782. Min Act: -0.1700
Data Index: 4605463 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.3469. Min Act: -0.1700
Data Index: 4537112 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2844. Min Range: -8.2844
Max Act: 7.3157. Min Act: -0.1700
Data Index: 983874 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19