Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4513. Min Range: -6.4513
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7718035 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4513. Min Range: -6.4513
Max Act: 6.1388. Min Act: -0.1700
Data Index: 4821965 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4513. Min Range: -6.4513
Max Act: 6.0138. Min Act: -0.1700
Data Index: 8782468 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4513. Min Range: -6.4513
Max Act: 6.0138. Min Act: -0.1700
Data Index: 3317442 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.9826. Min Act: -0.1700
Data Index: 7947309 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.9513. Min Act: -0.1700
Data Index: 18216 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.9201. Min Act: -0.1700
Data Index: 7988167 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.9201. Min Act: -0.1700
Data Index: 4829060 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.9201. Min Act: -0.1700
Data Index: 177793 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8888. Min Act: -0.1700
Data Index: 955554 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8888. Min Act: -0.1700
Data Index: 3568486 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8888. Min Act: -0.1700
Data Index: 3617860 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8888. Min Act: -0.1700
Data Index: 1789868 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8888. Min Act: -0.1700
Data Index: 7184139 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5033906 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3366485 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3158825 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.7951. Min Act: -0.1700
Data Index: 6273013 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.7951. Min Act: -0.1700
Data Index: 3888162 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4513. Min Range: -6.4513
Max Act: 5.7951. Min Act: -0.1700
Data Index: 4243359 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19