Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4342855 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.4740. Min Act: -0.1700
Data Index: 4946097 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.4115. Min Act: -0.1700
Data Index: 7667447 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.4428. Min Act: -0.1700
Data Index: 8281562 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.3490. Min Act: -0.1700
Data Index: 3471920 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3200205 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.3803. Min Act: -0.1700
Data Index: 2297650 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.3178. Min Act: -0.1700
Data Index: 8479103 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.3490. Min Act: -0.1700
Data Index: 6294285 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.2553. Min Act: -0.1700
Data Index: 5983463 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.2865. Min Act: -0.1700
Data Index: 4506617 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.2553. Min Act: -0.1700
Data Index: 1471609 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.2240. Min Act: -0.1700
Data Index: 8784096 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.2240. Min Act: -0.1700
Data Index: 4949875 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.1615. Min Act: -0.1700
Data Index: 5649292 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.1615. Min Act: -0.1700
Data Index: 7918526 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.1303. Min Act: -0.1700
Data Index: 1578232 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.0990. Min Act: -0.1700
Data Index: 2253622 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.0365. Min Act: -0.1700
Data Index: 5529273 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5053. Min Range: -6.5053
Max Act: 6.0678. Min Act: -0.1700
Data Index: 6535973 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19