Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.8683. Min Act: -0.1700
Data Index: 1034045 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.7746. Min Act: -0.1700
Data Index: 4956458 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.5558. Min Act: -0.1700
Data Index: 4390440 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.4933. Min Act: -0.1700
Data Index: 5485622 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.5246. Min Act: -0.1700
Data Index: 7584815 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.5246. Min Act: -0.1700
Data Index: 1187207 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.5246. Min Act: -0.1700
Data Index: 8067436 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.4621. Min Act: -0.1700
Data Index: 8732432 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3996. Min Act: -0.1700
Data Index: 1761658 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3996. Min Act: -0.1700
Data Index: 6491095 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.4308. Min Act: -0.1700
Data Index: 2238751 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3683. Min Act: -0.1700
Data Index: 1310349 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3683. Min Act: -0.1700
Data Index: 2168540 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3996. Min Act: -0.1700
Data Index: 3352300 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3371. Min Act: -0.1700
Data Index: 8020910 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3058. Min Act: -0.1700
Data Index: 7575678 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3371. Min Act: -0.1700
Data Index: 2504804 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3058. Min Act: -0.1700
Data Index: 2093853 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.3058. Min Act: -0.1700
Data Index: 520220 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8683. Min Range: -5.8683
Max Act: 5.2746. Min Act: -0.1700
Data Index: 2745725 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19