Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4181 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.1299. Min Act: -0.1700
Data Index: 7051136 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.0510. Min Act: -0.1700
Data Index: 6379118 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.0353. Min Act: -0.1700
Data Index: 4971811 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.0195. Min Act: -0.1700
Data Index: 6410506 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.0195. Min Act: -0.1700
Data Index: 7295438 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1299. Min Range: -3.1299
Max Act: 3.0037. Min Act: -0.1700
Data Index: 509335 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.9562. Min Act: -0.1700
Data Index: 3422277 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.9246. Min Act: -0.1700
Data Index: 7803556 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.9087. Min Act: -0.1700
Data Index: 3220678 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.9087. Min Act: -0.1700
Data Index: 6657355 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8929. Min Act: -0.1700
Data Index: 3444154 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8929. Min Act: -0.1700
Data Index: 2325048 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8929. Min Act: -0.1700
Data Index: 5715805 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 1593088 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 5940344 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 843729 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 8376357 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 2861454 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8611. Min Act: -0.1700
Data Index: 8683841 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1299. Min Range: -3.1299
Max Act: 2.8770. Min Act: -0.1700
Data Index: 5054758 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19