Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.6803. Min Act: -0.1700
Data Index: 5644210 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.2741. Min Act: -0.1700
Data Index: 6584930 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.0553. Min Act: -0.1700
Data Index: 3667010 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.0553. Min Act: -0.1700
Data Index: 3628474 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.0241. Min Act: -0.1700
Data Index: 7224353 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6803. Min Range: -6.6803
Max Act: 6.0241. Min Act: -0.1700
Data Index: 3775610 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.9928. Min Act: -0.1700
Data Index: 4263899 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.9928. Min Act: -0.1700
Data Index: 234365 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8991. Min Act: -0.1700
Data Index: 3981441 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.9303. Min Act: -0.1700
Data Index: 4645165 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.9303. Min Act: -0.1700
Data Index: 461385 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8991. Min Act: -0.1700
Data Index: 671039 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8991. Min Act: -0.1700
Data Index: 4353050 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8678. Min Act: -0.1700
Data Index: 7297134 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8678. Min Act: -0.1700
Data Index: 7670897 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 4409480 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 4298628 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 3423594 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8366. Min Act: -0.1700
Data Index: 2069793 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6803. Min Range: -6.6803
Max Act: 5.8053. Min Act: -0.1700
Data Index: 609248 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19