Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3559. Min Act: -0.1700
Data Index: 862802 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1475801 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.3246. Min Act: -0.1700
Data Index: 5240315 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2934. Min Act: -0.1700
Data Index: 4145087 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2934. Min Act: -0.1700
Data Index: 5257204 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 920210 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 2818649 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 5453151 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 752233 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 2028357 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2621. Min Act: -0.1700
Data Index: 4575908 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2309. Min Act: -0.1700
Data Index: 659500 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4575912 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2309. Min Act: -0.1700
Data Index: 6753005 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1683. Min Act: -0.1700
Data Index: 1128800 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2309. Min Act: -0.1700
Data Index: 6578931 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1996. Min Act: -0.1700
Data Index: 4575904 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2309. Min Act: -0.1700
Data Index: 4563502 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.1996. Min Act: -0.1700
Data Index: 6671973 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3559. Min Range: -4.3559
Max Act: 4.2309. Min Act: -0.1700
Data Index: 604118 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19