Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2680. Min Range: -5.2680
Max Act: 5.2680. Min Act: -0.1700
Data Index: 2472980 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2680. Min Range: -5.2680
Max Act: 5.1117. Min Act: -0.1700
Data Index: 6774390 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2680. Min Range: -5.2680
Max Act: 5.0805. Min Act: -0.1700
Data Index: 5703025 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2680. Min Range: -5.2680
Max Act: 5.0180. Min Act: -0.1700
Data Index: 2663058 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9555. Min Act: -0.1700
Data Index: 890712 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9555. Min Act: -0.1700
Data Index: 2773968 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9555. Min Act: -0.1700
Data Index: 5355812 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9555. Min Act: -0.1700
Data Index: 5615635 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9555. Min Act: -0.1700
Data Index: 1902379 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.9242. Min Act: -0.1700
Data Index: 2769904 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.8930. Min Act: -0.1700
Data Index: 64045 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.8617. Min Act: -0.1700
Data Index: 5264893 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.7992. Min Act: -0.1700
Data Index: 6252030 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.7680. Min Act: -0.1700
Data Index: 4248669 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.7055. Min Act: -0.1700
Data Index: 5246694 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.7055. Min Act: -0.1700
Data Index: 5325727 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.7367. Min Act: -0.1700
Data Index: 2033677 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.6742. Min Act: -0.1700
Data Index: 6627196 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.6742. Min Act: -0.1700
Data Index: 7571099 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2680. Min Range: -5.2680
Max Act: 4.6742. Min Act: -0.1700
Data Index: 8475793 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19