Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.1675. Min Act: -0.1700
Data Index: 356753 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.1050. Min Act: -0.1700
Data Index: 7072225 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.0737. Min Act: -0.1700
Data Index: 915700 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.0893. Min Act: -0.1700
Data Index: 289773 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.0112. Min Act: -0.1700
Data Index: 4363609 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9956. Min Act: -0.1699
Data Index: 3260477 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9956. Min Act: -0.1700
Data Index: 1812177 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1675. Min Range: -4.1675
Max Act: 4.0112. Min Act: -0.1699
Data Index: 4183966 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9799. Min Act: -0.1700
Data Index: 289772 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9799. Min Act: -0.1700
Data Index: 3079141 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1700
Data Index: 6588824 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1695
Data Index: 5369420 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1700
Data Index: 6685812 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1700
Data Index: 3166944 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1668
Data Index: 1339405 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9330. Min Act: -0.1700
Data Index: 2745951 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9487. Min Act: -0.1700
Data Index: 5755364 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9174. Min Act: -0.1700
Data Index: 689457 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9174. Min Act: -0.1700
Data Index: 6260474 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1675. Min Range: -4.1675
Max Act: 3.9018. Min Act: -0.1700
Data Index: 4306185 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19