Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.3235. Min Act: -0.1700
Data Index: 1689808 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.2610. Min Act: -0.1700
Data Index: 1480515 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.1985. Min Act: -0.1700
Data Index: 4507885 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.1360. Min Act: -0.1700
Data Index: 5546316 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.0735. Min Act: -0.1700
Data Index: 7748678 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.0422. Min Act: -0.1700
Data Index: 3062961 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.0422. Min Act: -0.1700
Data Index: 6143073 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9797. Min Act: -0.1700
Data Index: 1480510 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3235. Min Range: -8.3235
Max Act: 8.0422. Min Act: -0.1700
Data Index: 3848846 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9485. Min Act: -0.1700
Data Index: 8096646 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9485. Min Act: -0.1700
Data Index: 6143059 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9172. Min Act: -0.1700
Data Index: 654216 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9172. Min Act: -0.1700
Data Index: 94944 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.9172. Min Act: -0.1700
Data Index: 7263502 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8860. Min Act: -0.1700
Data Index: 6664718 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8860. Min Act: -0.1700
Data Index: 8079913 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8860. Min Act: -0.1700
Data Index: 5699760 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8547. Min Act: -0.1700
Data Index: 8575635 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1595624 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3235. Min Range: -8.3235
Max Act: 7.8547. Min Act: -0.1700
Data Index: 5095788 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19