Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2328 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.6637. Min Act: -0.1700
Data Index: 7636921 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.5385. Min Act: -0.1700
Data Index: 6789627 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4602. Min Act: -0.1700
Data Index: 2844049 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 2494933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3432943 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1310299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1903817 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3069179 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1717745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 6659962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1717666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 6222723 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 4662063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3401905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3268019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3181966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1628057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 1972576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 3074861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6637. Min Range: -3.6637
Max Act: 3.4445. Min Act: -0.1700
Data Index: 2367665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19