Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.3644. Min Act: -0.1700
Data Index: 4110548 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.3019. Min Act: -0.1700
Data Index: 5467604 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.1769. Min Act: -0.1700
Data Index: 6745174 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.1769. Min Act: -0.1700
Data Index: 7368446 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.1144. Min Act: -0.1700
Data Index: 7395161 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.0519. Min Act: -0.1700
Data Index: 6564485 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3644. Min Range: -8.3644
Max Act: 8.0519. Min Act: -0.1700
Data Index: 1225539 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9894. Min Act: -0.1700
Data Index: 2394625 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9894. Min Act: -0.1700
Data Index: 7634350 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9894. Min Act: -0.1700
Data Index: 2548375 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9894. Min Act: -0.1700
Data Index: 7935226 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9269. Min Act: -0.1700
Data Index: 6600551 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9269. Min Act: -0.1700
Data Index: 404848 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.9269. Min Act: -0.1700
Data Index: 5804416 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8644. Min Act: -0.1700
Data Index: 1662433 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8644. Min Act: -0.1700
Data Index: 8003368 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8644. Min Act: -0.1700
Data Index: 5583110 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8644. Min Act: -0.1700
Data Index: 5434117 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8019. Min Act: -0.1700
Data Index: 598841 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3644. Min Range: -8.3644
Max Act: 7.8019. Min Act: -0.1700
Data Index: 2915535 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19