Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6952. Min Range: -8.6952
Max Act: 8.6952. Min Act: -0.1700
Data Index: 8146772 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6952. Min Range: -8.6952
Max Act: 8.0702. Min Act: -0.1700
Data Index: 3204674 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6952. Min Range: -8.6952
Max Act: 8.0389. Min Act: -0.1700
Data Index: 8102713 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.9452. Min Act: -0.1700
Data Index: 1523823 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.8827. Min Act: -0.1700
Data Index: 8786287 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.8827. Min Act: -0.1700
Data Index: 1731875 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.7889. Min Act: -0.1700
Data Index: 2371010 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.7577. Min Act: -0.1700
Data Index: 6864789 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6327. Min Act: -0.1700
Data Index: 8357798 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6639. Min Act: -0.1700
Data Index: 8429632 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6639. Min Act: -0.1700
Data Index: 1823130 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6639. Min Act: -0.1700
Data Index: 2799337 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6327. Min Act: -0.1700
Data Index: 5859090 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6014. Min Act: -0.1700
Data Index: 7472852 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6327. Min Act: -0.1700
Data Index: 217513 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6014. Min Act: -0.1700
Data Index: 2329689 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6014. Min Act: -0.1700
Data Index: 2373667 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.6014. Min Act: -0.1700
Data Index: 7416827 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.5077. Min Act: -0.1700
Data Index: 3222936 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6952. Min Range: -8.6952
Max Act: 7.5389. Min Act: -0.1700
Data Index: 2565826 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19