Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0233. Min Range: -5.0233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 1907402 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.8045. Min Act: -0.1700
Data Index: 8606146 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.8045. Min Act: -0.1700
Data Index: 6621020 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7420. Min Act: -0.1700
Data Index: 6161438 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7733. Min Act: -0.1700
Data Index: 2288702 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7733. Min Act: -0.1700
Data Index: 8644027 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7420. Min Act: -0.1700
Data Index: 7754118 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7108. Min Act: -0.1700
Data Index: 8533818 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7108. Min Act: -0.1700
Data Index: 6249496 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7420. Min Act: -0.1700
Data Index: 110005 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7108. Min Act: -0.1700
Data Index: 453834 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7108. Min Act: -0.1700
Data Index: 8683800 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7420. Min Act: -0.1700
Data Index: 6845875 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1270875 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6795. Min Act: -0.1700
Data Index: 276115 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6795. Min Act: -0.1700
Data Index: 2533906 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6795. Min Act: -0.1700
Data Index: 4706311 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6483. Min Act: -0.1700
Data Index: 5637755 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6483. Min Act: -0.1700
Data Index: 2016250 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6483. Min Act: -0.1700
Data Index: 2937650 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19