Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2845. Min Range: -6.2845
Max Act: 6.2845. Min Act: -0.1700
Data Index: 5823486 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2845. Min Range: -6.2845
Max Act: 6.0345. Min Act: -0.1700
Data Index: 4786731 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.8157. Min Act: -0.1700
Data Index: 2291892 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.8157. Min Act: -0.1700
Data Index: 3737901 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.8157. Min Act: -0.1700
Data Index: 8352831 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1275843 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.6595. Min Act: -0.1700
Data Index: 5409349 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.6595. Min Act: -0.1700
Data Index: 1464608 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.6595. Min Act: -0.1700
Data Index: 8352830 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.6282. Min Act: -0.1700
Data Index: 5616516 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5970. Min Act: -0.1700
Data Index: 1012322 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.6282. Min Act: -0.1700
Data Index: 3222780 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5970. Min Act: -0.1700
Data Index: 6287178 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5970. Min Act: -0.1700
Data Index: 2720078 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5657. Min Act: -0.1700
Data Index: 3003038 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5657. Min Act: -0.1700
Data Index: 8303340 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5657. Min Act: -0.1700
Data Index: 2605483 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5240989 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5657. Min Act: -0.1700
Data Index: 745991 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2845. Min Range: -6.2845
Max Act: 5.5345. Min Act: -0.1700
Data Index: 321994 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19