Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.6526. Min Act: -0.1700
Data Index: 1806668 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.6214. Min Act: -0.1700
Data Index: 594133 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.6214. Min Act: -0.1700
Data Index: 1806662 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.5901. Min Act: -0.1695
Data Index: 1658293 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.5589. Min Act: -0.1700
Data Index: 885831 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.5589. Min Act: -0.1694
Data Index: 1806667 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.5589. Min Act: -0.1696
Data Index: 1806671 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.5276. Min Act: -0.1699
Data Index: 7476692 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4964. Min Act: -0.1700
Data Index: 6173038 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4964. Min Act: -0.1700
Data Index: 594151 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4964. Min Act: -0.1700
Data Index: 4527323 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4339. Min Act: -0.1700
Data Index: 5479363 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6611124 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4026. Min Act: -0.1700
Data Index: 7485631 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4026. Min Act: -0.1700
Data Index: 5253625 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.4026. Min Act: -0.1684
Data Index: 1806666 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.3714. Min Act: -0.1700
Data Index: 1978068 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.3714. Min Act: -0.1700
Data Index: 7105726 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.3401. Min Act: -0.1700
Data Index: 7452836 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6526. Min Range: -5.6526
Max Act: 5.3714. Min Act: -0.1700
Data Index: 3117297 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19