Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.9496. Min Act: -0.1700
Data Index: 5203808 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.7934. Min Act: -0.1700
Data Index: 6845256 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.6371. Min Act: -0.1700
Data Index: 3728569 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.6684. Min Act: -0.1700
Data Index: 1352449 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.5746. Min Act: -0.1700
Data Index: 5897138 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.5434. Min Act: -0.1700
Data Index: 8707281 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.5121. Min Act: -0.1700
Data Index: 3138127 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.4809. Min Act: -0.1700
Data Index: 5824424 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.4496. Min Act: -0.1700
Data Index: 915622 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.4496. Min Act: -0.1700
Data Index: 2120821 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4819231 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3559. Min Act: -0.1700
Data Index: 5085448 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3559. Min Act: -0.1700
Data Index: 6952405 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3246. Min Act: -0.1700
Data Index: 1624665 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.2934. Min Act: -0.1700
Data Index: 6745149 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.2934. Min Act: -0.1700
Data Index: 7075439 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3246. Min Act: -0.1700
Data Index: 3143088 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3246. Min Act: -0.1700
Data Index: 2711013 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.2934. Min Act: -0.1700
Data Index: 7224546 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9496. Min Range: -6.9496
Max Act: 6.3246. Min Act: -0.1700
Data Index: 992224 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19