Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0809. Min Range: -8.0809
Max Act: 8.0809. Min Act: -0.1700
Data Index: 114554 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.8309. Min Act: -0.1700
Data Index: 3699530 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.7684. Min Act: -0.1700
Data Index: 4435633 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.6434. Min Act: -0.1700
Data Index: 8062980 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.6121. Min Act: -0.1700
Data Index: 5787766 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.5496. Min Act: -0.1700
Data Index: 1892342 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.5809. Min Act: -0.1700
Data Index: 833030 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.5184. Min Act: -0.1700
Data Index: 7269318 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.4559. Min Act: -0.1700
Data Index: 4338443 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.4246. Min Act: -0.1700
Data Index: 8197389 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.4246. Min Act: -0.1700
Data Index: 7505717 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.4246. Min Act: -0.1700
Data Index: 2710301 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.3934. Min Act: -0.1700
Data Index: 4458416 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.3621. Min Act: -0.1700
Data Index: 5986748 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.2996. Min Act: -0.1700
Data Index: 5109344 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.3621. Min Act: -0.1700
Data Index: 3570067 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.2996. Min Act: -0.1700
Data Index: 2063516 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.2996. Min Act: -0.1700
Data Index: 516118 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.2684. Min Act: -0.1700
Data Index: 3965120 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0809. Min Range: -8.0809
Max Act: 7.2996. Min Act: -0.1700
Data Index: 8634413 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19