Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0209. Min Range: -4.0209
Max Act: 4.0209. Min Act: -0.1700
Data Index: 6892940 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.9271. Min Act: -0.1700
Data Index: 6171766 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8959. Min Act: -0.1700
Data Index: 6438976 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8646. Min Act: -0.1700
Data Index: 2225320 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 4960065 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 3219336 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 4951551 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 487852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 8313522 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 2071088 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.7708. Min Act: -0.1700
Data Index: 2843401 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8021. Min Act: -0.1700
Data Index: 3855010 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8021. Min Act: -0.1700
Data Index: 722123 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8021. Min Act: -0.1700
Data Index: 4708942 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.7708. Min Act: -0.1700
Data Index: 2395252 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8333. Min Act: -0.1700
Data Index: 7815903 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.7708. Min Act: -0.1700
Data Index: 4836313 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.8021. Min Act: -0.1700
Data Index: 7840861 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.7708. Min Act: -0.1700
Data Index: 797545 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0209. Min Range: -4.0209
Max Act: 3.7708. Min Act: -0.1700
Data Index: 786728 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19