Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.1477. Min Act: -0.1700
Data Index: 3843143 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.0852. Min Act: -0.1700
Data Index: 3771388 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.0540. Min Act: -0.1700
Data Index: 4618965 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.0540. Min Act: -0.1700
Data Index: 7396800 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.0540. Min Act: -0.1700
Data Index: 6803472 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1477. Min Range: -4.1477
Max Act: 4.0540. Min Act: -0.1700
Data Index: 1025933 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9915. Min Act: -0.1700
Data Index: 735303 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9915. Min Act: -0.1700
Data Index: 6990905 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 503861 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9915. Min Act: -0.1700
Data Index: 7759964 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 2143090 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9289. Min Act: -0.1700
Data Index: 84435 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 771466 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 6069198 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 5660197 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 5248568 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 2256273 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9602. Min Act: -0.1700
Data Index: 8493918 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9289. Min Act: -0.1700
Data Index: 3751244 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1477. Min Range: -4.1477
Max Act: 3.9289. Min Act: -0.1700
Data Index: 980301 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19