Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5862 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.3486. Min Act: -0.1700
Data Index: 1414078 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.3174. Min Act: -0.1700
Data Index: 59194 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.2549. Min Act: -0.1700
Data Index: 5195710 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0986. Min Act: -0.1700
Data Index: 1553658 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0674. Min Act: -0.1700
Data Index: 6008857 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0361. Min Act: -0.1700
Data Index: 2339338 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0674. Min Act: -0.1700
Data Index: 7779739 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0361. Min Act: -0.1700
Data Index: 7183497 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.9736. Min Act: -0.1700
Data Index: 3876787 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3486. Min Range: -5.3486
Max Act: 5.0049. Min Act: -0.1700
Data Index: 7324770 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.9111. Min Act: -0.1700
Data Index: 5108066 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.9424. Min Act: -0.1700
Data Index: 2086473 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.9111. Min Act: -0.1700
Data Index: 351686 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 8191000 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.9111. Min Act: -0.1700
Data Index: 5906611 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 7681915 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1356931 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1553651 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 424868 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3486. Min Range: -5.3486
Max Act: 4.8799. Min Act: -0.1700
Data Index: 669429 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19