Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.4380. Min Act: -0.1700
Data Index: 5529470 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3755. Min Act: -0.1700
Data Index: 1189591 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.3442. Min Act: -0.1700
Data Index: 6645035 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2817. Min Act: -0.1700
Data Index: 7655549 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2504. Min Act: -0.1700
Data Index: 4669515 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2192. Min Act: -0.1700
Data Index: 4669516 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.2192. Min Act: -0.1700
Data Index: 5446949 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.1879. Min Act: -0.1700
Data Index: 7502214 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.1567. Min Act: -0.1700
Data Index: 5376631 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.1254. Min Act: -0.1700
Data Index: 4669517 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0942. Min Act: -0.1700
Data Index: 6850058 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0942. Min Act: -0.1700
Data Index: 6286830 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0942. Min Act: -0.1700
Data Index: 7238857 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0629. Min Act: -0.1700
Data Index: 319333 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0629. Min Act: -0.1700
Data Index: 4502798 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0629. Min Act: -0.1700
Data Index: 6850080 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0317. Min Act: -0.1700
Data Index: 7502213 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0317. Min Act: -0.1700
Data Index: 3726201 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0317. Min Act: -0.1700
Data Index: 851188 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4380. Min Range: -4.4380
Max Act: 4.0004. Min Act: -0.1700
Data Index: 1125441 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19