Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4440 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2208. Min Range: -8.2208
Max Act: 8.2208. Min Act: -0.1700
Data Index: 6678548 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2208. Min Range: -8.2208
Max Act: 8.0958. Min Act: -0.1700
Data Index: 2917104 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2208. Min Range: -8.2208
Max Act: 8.0958. Min Act: -0.1700
Data Index: 7988812 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2208. Min Range: -8.2208
Max Act: 8.1583. Min Act: -0.1700
Data Index: 8733832 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 1882119 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.9083. Min Act: -0.1700
Data Index: 5859557 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.8458. Min Act: -0.1700
Data Index: 3935720 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7833. Min Act: -0.1700
Data Index: 8671049 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7833. Min Act: -0.1700
Data Index: 3821307 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7208. Min Act: -0.1700
Data Index: 5384614 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7208. Min Act: -0.1700
Data Index: 6058013 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7208. Min Act: -0.1700
Data Index: 1393300 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.7208. Min Act: -0.1700
Data Index: 5543023 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 637753 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 5451150 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 8720854 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 1537118 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 8134239 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.6583. Min Act: -0.1700
Data Index: 6188813 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2208. Min Range: -8.2208
Max Act: 7.5958. Min Act: -0.1700
Data Index: 8263718 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19