Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.9065. Min Act: -0.1700
Data Index: 4710483 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8748. Min Act: -0.1700
Data Index: 552236 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8589. Min Act: -0.1700
Data Index: 3511472 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8271. Min Act: -0.1700
Data Index: 1549992 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8589. Min Act: -0.1700
Data Index: 5698825 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8112. Min Act: -0.1700
Data Index: 5158411 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.8112. Min Act: -0.1700
Data Index: 4908382 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7475. Min Act: -0.1700
Data Index: 5024797 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7315. Min Act: -0.1700
Data Index: 5036646 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7315. Min Act: -0.1700
Data Index: 6678810 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7315. Min Act: -0.1700
Data Index: 7697190 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7155. Min Act: -0.1700
Data Index: 3605582 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.7155. Min Act: -0.1700
Data Index: 4119546 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6995. Min Act: -0.1700
Data Index: 174322 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6995. Min Act: -0.1700
Data Index: 8379498 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6835. Min Act: -0.1700
Data Index: 8464140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6995. Min Act: -0.1700
Data Index: 6472923 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6835. Min Act: -0.1700
Data Index: 799986 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6835. Min Act: -0.1700
Data Index: 375292 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9065. Min Range: -2.9065
Max Act: 2.6835. Min Act: -0.1700
Data Index: 3695191 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19