Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4815. Min Act: -0.1700
Data Index: 1203612 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4815. Min Act: -0.1700
Data Index: 4208179 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4815. Min Act: -0.1700
Data Index: 8087180 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4815. Min Act: -0.1700
Data Index: 6393635 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4190. Min Act: -0.1700
Data Index: 4398407 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3565. Min Act: -0.1700
Data Index: 5279545 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3565. Min Act: -0.1700
Data Index: 651385 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3565. Min Act: -0.1700
Data Index: 3998665 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3565. Min Act: -0.1700
Data Index: 7116301 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3252. Min Act: -0.1700
Data Index: 6655193 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 3163063 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.3252. Min Act: -0.1700
Data Index: 7833672 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 6747392 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2627. Min Act: -0.1700
Data Index: 4945744 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 1588089 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 652157 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 6091639 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2315. Min Act: -0.1700
Data Index: 5944184 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2627. Min Act: -0.1700
Data Index: 5609597 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2627. Min Act: -0.1700
Data Index: 988497 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19