Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.4302. Min Act: -0.1697
Data Index: 4285156 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.4139. Min Act: -0.1700
Data Index: 1149209 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3976. Min Act: -0.1700
Data Index: 604052 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3813. Min Act: -0.1700
Data Index: 5843599 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3976. Min Act: -0.1574
Data Index: 5465 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3649. Min Act: -0.1698
Data Index: 5309082 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3649. Min Act: -0.1698
Data Index: 6725816 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3485. Min Act: -0.1699
Data Index: 2720316 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3485. Min Act: -0.1700
Data Index: 7322724 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3485. Min Act: -0.1700
Data Index: 1166463 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3157. Min Act: -0.1692
Data Index: 5464 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2993. Min Act: -0.1699
Data Index: 3253594 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.3157. Min Act: -0.1684
Data Index: 5827168 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2993. Min Act: -0.1700
Data Index: 4513727 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2993. Min Act: -0.1698
Data Index: 8698948 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2828. Min Act: -0.1695
Data Index: 2621701 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2828. Min Act: -0.1700
Data Index: 2875516 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2498. Min Act: -0.1700
Data Index: 71777 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2663. Min Act: -0.1616
Data Index: 966109 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4302. Min Range: -2.4302
Max Act: 2.2663. Min Act: -0.1698
Data Index: 1597128 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19