Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1738 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.2644. Min Act: -0.1700
Data Index: 6545179 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.2332. Min Act: -0.1700
Data Index: 8666910 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.2644. Min Act: -0.1700
Data Index: 7471744 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.2019. Min Act: -0.1700
Data Index: 7036070 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1707. Min Act: -0.1700
Data Index: 7441720 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1707. Min Act: -0.1700
Data Index: 6197364 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1707. Min Act: -0.1700
Data Index: 1305546 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.2019. Min Act: -0.1700
Data Index: 6942275 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1082. Min Act: -0.1700
Data Index: 741954 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1394. Min Act: -0.1700
Data Index: 6966934 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1394. Min Act: -0.1700
Data Index: 7531575 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1082. Min Act: -0.1700
Data Index: 5318727 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.1082. Min Act: -0.1700
Data Index: 1279158 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0769. Min Act: -0.1692
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0769. Min Act: -0.1700
Data Index: 8597797 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0457. Min Act: -0.1700
Data Index: 1702197 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0457. Min Act: -0.1700
Data Index: 1674178 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0457. Min Act: -0.1700
Data Index: 8467489 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0457. Min Act: -0.1700
Data Index: 860102 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2644. Min Range: -6.2644
Max Act: 6.0457. Min Act: -0.1700
Data Index: 44302 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19