Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5408. Min Range: -9.5408
Max Act: 9.5408. Min Act: -0.1700
Data Index: 5449706 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5408. Min Range: -9.5408
Max Act: 9.4158. Min Act: -0.1700
Data Index: 1559743 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5408. Min Range: -9.5408
Max Act: 9.1658. Min Act: -0.1700
Data Index: 40388 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.9783. Min Act: -0.1700
Data Index: 4420788 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.9783. Min Act: -0.1700
Data Index: 375856 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.8533. Min Act: -0.1700
Data Index: 4774694 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.8533. Min Act: -0.1700
Data Index: 4191241 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.7908. Min Act: -0.1700
Data Index: 4304038 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.7908. Min Act: -0.1700
Data Index: 6970799 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.7283. Min Act: -0.1700
Data Index: 6855140 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.7283. Min Act: -0.1700
Data Index: 6772756 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.6658. Min Act: -0.1700
Data Index: 1708317 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.6658. Min Act: -0.1700
Data Index: 6477938 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.6658. Min Act: -0.1700
Data Index: 8284350 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.6033. Min Act: -0.1700
Data Index: 5344741 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.6033. Min Act: -0.1700
Data Index: 4911517 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.5408. Min Act: -0.1700
Data Index: 1800863 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.5408. Min Act: -0.1700
Data Index: 2761508 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.5408. Min Act: -0.1700
Data Index: 3404861 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5408. Min Range: -9.5408
Max Act: 8.5408. Min Act: -0.1700
Data Index: 4854929 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19