Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.4460. Min Act: -0.1700
Data Index: 3325630 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.2585. Min Act: -0.1700
Data Index: 4175661 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.1647. Min Act: -0.1700
Data Index: 8321974 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.1335. Min Act: -0.1700
Data Index: 2885964 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.0710. Min Act: -0.1700
Data Index: 6477329 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.0397. Min Act: -0.1700
Data Index: 5941259 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4460. Min Range: -5.4460
Max Act: 5.0085. Min Act: -0.1700
Data Index: 6476563 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 373774 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 7571305 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 5820715 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 4615185 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9460. Min Act: -0.1700
Data Index: 6093956 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.9147. Min Act: -0.1700
Data Index: 6328494 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8835. Min Act: -0.1700
Data Index: 6477335 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8835. Min Act: -0.1700
Data Index: 7571304 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8835. Min Act: -0.1700
Data Index: 6477339 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8835. Min Act: -0.1700
Data Index: 5894306 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 1002215 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 6550916 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4460. Min Range: -5.4460
Max Act: 4.8522. Min Act: -0.1700
Data Index: 7540914 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19