Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6239 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0734. Min Range: -5.0734
Max Act: 5.0734. Min Act: -0.1700
Data Index: 2148714 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.9171. Min Act: -0.1700
Data Index: 8348317 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.7921. Min Act: -0.1700
Data Index: 5341095 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.7296. Min Act: -0.1700
Data Index: 3496257 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6984. Min Act: -0.1700
Data Index: 7479456 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6984. Min Act: -0.1700
Data Index: 8178684 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6984. Min Act: -0.1700
Data Index: 1710125 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6671. Min Act: -0.1700
Data Index: 4635604 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6671. Min Act: -0.1700
Data Index: 4334441 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6359. Min Act: -0.1700
Data Index: 7797461 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6671. Min Act: -0.1700
Data Index: 3110521 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.6046. Min Act: -0.1700
Data Index: 167756 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5421. Min Act: -0.1700
Data Index: 2640574 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5734. Min Act: -0.1700
Data Index: 8703963 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5734. Min Act: -0.1700
Data Index: 288394 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5734. Min Act: -0.1700
Data Index: 1311136 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5734. Min Act: -0.1700
Data Index: 5913492 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5421. Min Act: -0.1700
Data Index: 3834098 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5109. Min Act: -0.1700
Data Index: 2586896 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0734. Min Range: -5.0734
Max Act: 4.5109. Min Act: -0.1700
Data Index: 5303983 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19