Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.9534. Min Act: -0.1700
Data Index: 3887439 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.8909. Min Act: -0.1700
Data Index: 18427 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.7659. Min Act: -0.1700
Data Index: 7554536 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.5784. Min Act: -0.1700
Data Index: 1570603 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.4534. Min Act: -0.1700
Data Index: 1801838 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.3909. Min Act: -0.1700
Data Index: 6867173 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.3909. Min Act: -0.1700
Data Index: 2697376 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.3909. Min Act: -0.1700
Data Index: 8288388 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.3284. Min Act: -0.1700
Data Index: 4371425 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.3284. Min Act: -0.1700
Data Index: 6271107 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2659. Min Act: -0.1700
Data Index: 7869686 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2659. Min Act: -0.1700
Data Index: 5322054 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2659. Min Act: -0.1700
Data Index: 8504381 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2659. Min Act: -0.1700
Data Index: 2590788 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 6023472 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 7507044 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 3725306 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 2889656 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 2889651 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9534. Min Range: -8.9534
Max Act: 8.2034. Min Act: -0.1700
Data Index: 3302683 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19