Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.2739. Min Act: -0.1700
Data Index: 6652786 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.1489. Min Act: -0.1700
Data Index: 6652785 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6652783 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9614. Min Act: -0.1699
Data Index: 870746 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8989. Min Act: -0.1700
Data Index: 6652780 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.7427. Min Act: -0.1700
Data Index: 6652782 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.6489. Min Act: -0.1700
Data Index: 4322611 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.6489. Min Act: -0.1700
Data Index: 6652781 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.6177. Min Act: -0.1694
Data Index: 1486136 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.5239. Min Act: -0.1700
Data Index: 6534833 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.5239. Min Act: -0.1700
Data Index: 6652784 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4927. Min Act: -0.1689
Data Index: 1584354 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4927. Min Act: -0.1700
Data Index: 5998058 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4614. Min Act: -0.1697
Data Index: 342647 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4614. Min Act: -0.1698
Data Index: 7245111 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4614. Min Act: -0.1700
Data Index: 3825698 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.4301. Min Act: -0.1700
Data Index: 2265247 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.3989. Min Act: -0.1700
Data Index: 1111632 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.3989. Min Act: -0.1700
Data Index: 954099 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.3364. Min Act: -0.1700
Data Index: 5668957 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19