Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.1578. Min Act: -0.1700
Data Index: 617329 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.1263. Min Act: -0.1700
Data Index: 1193149 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.1105. Min Act: -0.1700
Data Index: 2683428 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.0317. Min Act: -0.1700
Data Index: 617324 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.0632. Min Act: -0.1700
Data Index: 5629630 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1578. Min Range: -3.1578
Max Act: 3.0159. Min Act: -0.1700
Data Index: 3922051 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9843. Min Act: -0.1700
Data Index: 2891907 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9684. Min Act: -0.1700
Data Index: 5593954 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9843. Min Act: -0.1700
Data Index: 1853145 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9684. Min Act: -0.1700
Data Index: 1576981 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9684. Min Act: -0.1700
Data Index: 3852628 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9526. Min Act: -0.1700
Data Index: 3014019 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9684. Min Act: -0.1700
Data Index: 1193154 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9526. Min Act: -0.1700
Data Index: 5629629 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9209. Min Act: -0.1700
Data Index: 1576978 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.8734. Min Act: -0.1700
Data Index: 5593961 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.8892. Min Act: -0.1700
Data Index: 870983 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.9051. Min Act: -0.1700
Data Index: 5867613 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.8892. Min Act: -0.1700
Data Index: 602136 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1578. Min Range: -3.1578
Max Act: 2.8892. Min Act: -0.1700
Data Index: 4676921 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19