Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6112 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.9317. Min Act: -0.1700
Data Index: 2162986 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.7129. Min Act: -0.1700
Data Index: 5892190 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.6817. Min Act: -0.1700
Data Index: 7049099 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.5567. Min Act: -0.1700
Data Index: 6051055 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5863251 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.5567. Min Act: -0.1700
Data Index: 2849290 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.5254. Min Act: -0.1700
Data Index: 3496740 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4942. Min Act: -0.1700
Data Index: 5173764 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4942. Min Act: -0.1700
Data Index: 5929630 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4942. Min Act: -0.1700
Data Index: 7079160 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4629. Min Act: -0.1700
Data Index: 6550808 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4629. Min Act: -0.1700
Data Index: 325436 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4004. Min Act: -0.1700
Data Index: 4024252 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4317. Min Act: -0.1700
Data Index: 309499 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4004. Min Act: -0.1700
Data Index: 770501 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4004. Min Act: -0.1700
Data Index: 2253262 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.3692. Min Act: -0.1700
Data Index: 4606431 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.4004. Min Act: -0.1700
Data Index: 6898694 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.3379. Min Act: -0.1700
Data Index: 5708680 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9317. Min Range: -5.9317
Max Act: 5.3692. Min Act: -0.1700
Data Index: 799594 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19