Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.2293. Min Act: -0.1700
Data Index: 6525495 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1980. Min Act: -0.1700
Data Index: 6181422 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1355. Min Act: -0.1700
Data Index: 1857203 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1355. Min Act: -0.1700
Data Index: 4469134 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1043. Min Act: -0.1700
Data Index: 4827656 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1043. Min Act: -0.1700
Data Index: 2765158 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1588253 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.1043. Min Act: -0.1700
Data Index: 707050 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 2515501 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 7321865 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 8371877 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 7396369 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9480. Min Act: -0.1700
Data Index: 230253 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9793. Min Act: -0.1700
Data Index: 2210769 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9480. Min Act: -0.1700
Data Index: 1628399 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9480. Min Act: -0.1700
Data Index: 7070465 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9168. Min Act: -0.1700
Data Index: 802160 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9168. Min Act: -0.1700
Data Index: 8529526 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9168. Min Act: -0.1700
Data Index: 1398395 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8855. Min Act: -0.1700
Data Index: 5749030 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19