Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5128. Min Range: -9.5128
Max Act: 9.5128. Min Act: -0.1700
Data Index: 2600890 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5128. Min Range: -9.5128
Max Act: 9.0753. Min Act: -0.1700
Data Index: 4696879 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.8878. Min Act: -0.1700
Data Index: 5032575 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.7003. Min Act: -0.1700
Data Index: 4804813 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.5128. Min Act: -0.1700
Data Index: 1906160 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.5753. Min Act: -0.1700
Data Index: 5399540 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.6378. Min Act: -0.1700
Data Index: 5225925 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.5128. Min Act: -0.1700
Data Index: 6412193 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.4503. Min Act: -0.1700
Data Index: 5417238 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.4503. Min Act: -0.1700
Data Index: 3759054 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.3878. Min Act: -0.1700
Data Index: 2661175 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.4503. Min Act: -0.1700
Data Index: 7561449 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.3878. Min Act: -0.1700
Data Index: 6701603 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.3253. Min Act: -0.1700
Data Index: 3435828 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.3253. Min Act: -0.1700
Data Index: 6233771 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.2628. Min Act: -0.1700
Data Index: 1220471 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.2003. Min Act: -0.1700
Data Index: 762460 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.2003. Min Act: -0.1700
Data Index: 1652285 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.1378. Min Act: -0.1700
Data Index: 5417236 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5128. Min Range: -9.5128
Max Act: 8.2003. Min Act: -0.1700
Data Index: 517818 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19