Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0279. Min Range: -3.0279
Max Act: 3.0279. Min Act: -0.1700
Data Index: 1876821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.9330. Min Act: -0.1700
Data Index: 5947316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.7742. Min Act: -0.1700
Data Index: 747231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6943. Min Act: -0.1700
Data Index: 747232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.7103. Min Act: -0.1700
Data Index: 7398915 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6462. Min Act: -0.1700
Data Index: 2828582 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6301. Min Act: -0.1700
Data Index: 6002142 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6622. Min Act: -0.1700
Data Index: 2782635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6301. Min Act: -0.1700
Data Index: 794359 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6462. Min Act: -0.1700
Data Index: 8681292 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6943. Min Act: -0.1700
Data Index: 4936144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.5657. Min Act: -0.1700
Data Index: 5435394 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6141. Min Act: -0.1700
Data Index: 6421774 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6141. Min Act: -0.1700
Data Index: 1978181 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6141. Min Act: -0.1700
Data Index: 1198367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6141. Min Act: -0.1700
Data Index: 3008541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.6301. Min Act: -0.1700
Data Index: 5500859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.5980. Min Act: -0.1700
Data Index: 5366496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.5011. Min Act: -0.1700
Data Index: 1477604 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0279. Min Range: -3.0279
Max Act: 2.5657. Min Act: -0.1700
Data Index: 399499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19