Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.7623. Min Act: -0.1700
Data Index: 1003010 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7401323 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.7623. Min Act: -0.1700
Data Index: 8222136 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.7310. Min Act: -0.1700
Data Index: 5153802 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6998. Min Act: -0.1700
Data Index: 3879243 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6998. Min Act: -0.1700
Data Index: 5927951 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6685. Min Act: -0.1700
Data Index: 7900561 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 1978683 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6685. Min Act: -0.1700
Data Index: 1529523 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 4315282 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 8550362 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 8550363 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 2297651 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6373. Min Act: -0.1700
Data Index: 2741962 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6685. Min Act: -0.1700
Data Index: 2837982 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6060. Min Act: -0.1700
Data Index: 7324140 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6060. Min Act: -0.1700
Data Index: 4136346 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6060. Min Act: -0.1700
Data Index: 2806276 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.5748. Min Act: -0.1700
Data Index: 5562522 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7623. Min Range: -4.7623
Max Act: 4.6060. Min Act: -0.1700
Data Index: 2700660 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19