Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1393. Min Range: -6.1393
Max Act: 6.1393. Min Act: -0.1700
Data Index: 7548899 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.7018. Min Act: -0.1700
Data Index: 4587329 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.6393. Min Act: -0.1700
Data Index: 8557104 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.6080. Min Act: -0.1700
Data Index: 7800946 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.6080. Min Act: -0.1700
Data Index: 3989938 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.5768. Min Act: -0.1700
Data Index: 5487127 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.5455. Min Act: -0.1700
Data Index: 5688167 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.5455. Min Act: -0.1700
Data Index: 6374785 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.5143. Min Act: -0.1700
Data Index: 1194598 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.5455. Min Act: -0.1700
Data Index: 5188892 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4830. Min Act: -0.1700
Data Index: 7239578 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4830. Min Act: -0.1700
Data Index: 6333847 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4830. Min Act: -0.1700
Data Index: 6118482 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4830. Min Act: -0.1700
Data Index: 3600295 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4518. Min Act: -0.1700
Data Index: 4929332 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4830. Min Act: -0.1700
Data Index: 5487123 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4518. Min Act: -0.1700
Data Index: 4276089 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4518. Min Act: -0.1700
Data Index: 2279065 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4518. Min Act: -0.1700
Data Index: 6831445 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1393. Min Range: -6.1393
Max Act: 5.4518. Min Act: -0.1700
Data Index: 663759 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19