Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2398. Min Range: -5.2398
Max Act: 5.2398. Min Act: -0.1700
Data Index: 2345218 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2398. Min Range: -5.2398
Max Act: 5.1773. Min Act: -0.1700
Data Index: 7204749 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2398. Min Range: -5.2398
Max Act: 5.1461. Min Act: -0.1700
Data Index: 1356212 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2398. Min Range: -5.2398
Max Act: 5.0836. Min Act: -0.1700
Data Index: 3001525 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.9898. Min Act: -0.1700
Data Index: 4537865 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.9898. Min Act: -0.1700
Data Index: 1555145 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.9898. Min Act: -0.1700
Data Index: 2950601 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.9586. Min Act: -0.1700
Data Index: 2960167 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8961. Min Act: -0.1700
Data Index: 3057903 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.9273. Min Act: -0.1700
Data Index: 7576369 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8961. Min Act: -0.1700
Data Index: 1907713 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8648. Min Act: -0.1700
Data Index: 2668015 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8648. Min Act: -0.1700
Data Index: 7504327 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8648. Min Act: -0.1700
Data Index: 509040 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8336. Min Act: -0.1700
Data Index: 2372216 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8336. Min Act: -0.1700
Data Index: 3035671 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8023. Min Act: -0.1700
Data Index: 925118 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.8023. Min Act: -0.1700
Data Index: 7241357 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.7711. Min Act: -0.1700
Data Index: 2331429 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2398. Min Range: -5.2398
Max Act: 4.7711. Min Act: -0.1700
Data Index: 2515974 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19