Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1311. Min Range: -3.1311
Max Act: 3.1311. Min Act: -0.1700
Data Index: 5615335 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1311. Min Range: -3.1311
Max Act: 3.1311. Min Act: -0.1700
Data Index: 3531846 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1311. Min Range: -3.1311
Max Act: 3.0681. Min Act: -0.1700
Data Index: 257935 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1311. Min Range: -3.1311
Max Act: 3.0365. Min Act: -0.1700
Data Index: 7652083 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1311. Min Range: -3.1311
Max Act: 3.0049. Min Act: -0.1700
Data Index: 3037999 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9891. Min Act: -0.1700
Data Index: 3928997 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9733. Min Act: -0.1700
Data Index: 146498 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9733. Min Act: -0.1700
Data Index: 6033213 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9733. Min Act: -0.1700
Data Index: 3891023 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9575. Min Act: -0.1700
Data Index: 5877673 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9575. Min Act: -0.1700
Data Index: 8141 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9575. Min Act: -0.1700
Data Index: 1267820 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9416. Min Act: -0.1700
Data Index: 4983972 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9258. Min Act: -0.1700
Data Index: 4999231 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9100. Min Act: -0.1700
Data Index: 8120528 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9100. Min Act: -0.1700
Data Index: 4530071 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.9100. Min Act: -0.1700
Data Index: 8652245 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.8941. Min Act: -0.1700
Data Index: 1169675 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.8941. Min Act: -0.1700
Data Index: 825828 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1311. Min Range: -3.1311
Max Act: 2.8941. Min Act: -0.1700
Data Index: 4999831 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19