Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1163. Min Range: -6.1163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 446960 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.9600. Min Act: -0.1700
Data Index: 5038014 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7101281 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1981613 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7870473 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7725. Min Act: -0.1700
Data Index: 400750 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7725. Min Act: -0.1700
Data Index: 1089419 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7413. Min Act: -0.1700
Data Index: 3342744 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7413. Min Act: -0.1700
Data Index: 5158804 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7100. Min Act: -0.1700
Data Index: 2498287 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.7413. Min Act: -0.1700
Data Index: 7137051 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6475. Min Act: -0.1700
Data Index: 5155826 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6788. Min Act: -0.1700
Data Index: 3949528 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6475. Min Act: -0.1700
Data Index: 7101282 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6788. Min Act: -0.1700
Data Index: 7876342 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6475. Min Act: -0.1700
Data Index: 363232 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6163. Min Act: -0.1700
Data Index: 1105248 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6163. Min Act: -0.1700
Data Index: 3545203 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.5850. Min Act: -0.1700
Data Index: 1374448 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1163. Min Range: -6.1163
Max Act: 5.6163. Min Act: -0.1700
Data Index: 2914484 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19