Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5605 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6247524 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7691888 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8961. Min Act: -0.1700
Data Index: 3631754 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5721792 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8336. Min Act: -0.1700
Data Index: 7707797 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8336. Min Act: -0.1700
Data Index: 8431214 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5700380 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.8336. Min Act: -0.1700
Data Index: 6049061 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7711. Min Act: -0.1700
Data Index: 5819109 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7398. Min Act: -0.1700
Data Index: 506935 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7398. Min Act: -0.1700
Data Index: 7062930 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6773. Min Act: -0.1700
Data Index: 2281519 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7086. Min Act: -0.1700
Data Index: 7211183 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7398. Min Act: -0.1700
Data Index: 4213879 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6773. Min Act: -0.1700
Data Index: 6805494 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.7086. Min Act: -0.1700
Data Index: 8477235 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7032994 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6461. Min Act: -0.1700
Data Index: 6122304 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6461. Min Act: -0.1700
Data Index: 1417274 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9273. Min Range: -5.9273
Max Act: 5.6461. Min Act: -0.1700
Data Index: 5940301 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19