Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0569. Min Range: -9.0569
Max Act: 9.0569. Min Act: -0.1700
Data Index: 2703353 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.6194. Min Act: -0.1700
Data Index: 4636473 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.4944. Min Act: -0.1700
Data Index: 438493 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 4862686 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.4319. Min Act: -0.1700
Data Index: 3730551 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.4319. Min Act: -0.1700
Data Index: 13779 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 8184935 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 1598063 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 350312 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 3627870 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 1882412 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 8184922 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 5991747 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 522657 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 8484190 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 7989578 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 6630663 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 616231 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 1892531 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0569. Min Range: -9.0569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 2831765 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19