Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1578106 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1707. Min Act: -0.1700
Data Index: 7661581 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1394. Min Act: -0.1700
Data Index: 546891 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1394. Min Act: -0.1700
Data Index: 4898028 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1082. Min Act: -0.1700
Data Index: 5795812 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1082. Min Act: -0.1700
Data Index: 1495822 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.1082. Min Act: -0.1700
Data Index: 4180119 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 7677262 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 6046379 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 2993656 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 614313 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 2431836 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 1977935 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 6775511 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 36618 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 8663977 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0144. Min Act: -0.1700
Data Index: 4446111 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0144. Min Act: -0.1700
Data Index: 2574155 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0144. Min Act: -0.1700
Data Index: 6627402 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9832. Min Act: -0.1700
Data Index: 7679787 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19