Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4232 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2818. Min Range: -5.2818
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4078363 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2818. Min Range: -5.2818
Max Act: 5.0943. Min Act: -0.1700
Data Index: 683010 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9693. Min Act: -0.1700
Data Index: 5793433 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9693. Min Act: -0.1700
Data Index: 8334891 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9381. Min Act: -0.1700
Data Index: 1729525 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9381. Min Act: -0.1700
Data Index: 5388281 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9381. Min Act: -0.1700
Data Index: 6313125 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.9068. Min Act: -0.1700
Data Index: 6820220 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8756. Min Act: -0.1700
Data Index: 3298943 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8443. Min Act: -0.1700
Data Index: 6840805 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8443. Min Act: -0.1700
Data Index: 7044138 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8443. Min Act: -0.1700
Data Index: 5076487 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8131. Min Act: -0.1700
Data Index: 4874341 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8131. Min Act: -0.1700
Data Index: 2905434 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8131. Min Act: -0.1700
Data Index: 2355095 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8131. Min Act: -0.1700
Data Index: 6133885 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.7818. Min Act: -0.1700
Data Index: 1146519 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.8131. Min Act: -0.1700
Data Index: 2500463 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.7818. Min Act: -0.1700
Data Index: 2011939 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2818. Min Range: -5.2818
Max Act: 4.7818. Min Act: -0.1700
Data Index: 6339583 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19