Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.2400. Min Act: -0.1700
Data Index: 7974441 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.2068. Min Act: -0.1698
Data Index: 6996032 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.1236. Min Act: -0.1700
Data Index: 8411138 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.1236. Min Act: -0.1700
Data Index: 2356932 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.1570. Min Act: -0.1700
Data Index: 7536615 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.1236. Min Act: -0.1700
Data Index: 7338052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0901. Min Act: -0.1700
Data Index: 7185375 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0901. Min Act: -0.1700
Data Index: 2938534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0734. Min Act: -0.1700
Data Index: 1025527 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0398. Min Act: -0.1700
Data Index: 1102802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0566. Min Act: -0.1700
Data Index: 7504467 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0566. Min Act: -0.1700
Data Index: 4515333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0398. Min Act: -0.1700
Data Index: 85490 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0398. Min Act: -0.1700
Data Index: 8595959 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0229. Min Act: -0.1700
Data Index: 7181688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0060. Min Act: -0.1700
Data Index: 376090 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0229. Min Act: -0.1700
Data Index: 2646494 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2400. Min Range: -2.2400
Max Act: 1.9891. Min Act: -0.1700
Data Index: 4776642 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0229. Min Act: -0.1700
Data Index: 7214917 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2400. Min Range: -2.2400
Max Act: 2.0060. Min Act: -0.1700
Data Index: 2176632 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19