Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.5382. Min Act: -0.1700
Data Index: 251469 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.4757. Min Act: -0.1700
Data Index: 4524118 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3819. Min Act: -0.1700
Data Index: 3841804 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3194. Min Act: -0.1700
Data Index: 7746374 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3194. Min Act: -0.1700
Data Index: 3544347 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3194. Min Act: -0.1700
Data Index: 6696218 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3194. Min Act: -0.1700
Data Index: 2507858 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.3507. Min Act: -0.1700
Data Index: 5266334 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 3902583 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2882. Min Act: -0.1700
Data Index: 315285 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2882. Min Act: -0.1700
Data Index: 7905869 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 5338480 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 1208468 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 5681712 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 5158154 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2257. Min Act: -0.1700
Data Index: 2812974 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2569. Min Act: -0.1700
Data Index: 1406355 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.2257. Min Act: -0.1700
Data Index: 1313031 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.1944. Min Act: -0.1700
Data Index: 1089465 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5382. Min Range: -5.5382
Max Act: 5.1944. Min Act: -0.1700
Data Index: 733885 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19