Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 927 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.8153. Min Act: -0.1700
Data Index: 8827049 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5966. Min Act: -0.1700
Data Index: 8737378 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5653. Min Act: -0.1700
Data Index: 538736 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1700
Data Index: 3470229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1700
Data Index: 1297663 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1700
Data Index: 1721735 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1700
Data Index: 1750166 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5653. Min Act: -0.1700
Data Index: 4401353 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5653. Min Act: -0.1700
Data Index: 1956382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1685
Data Index: 2844299 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5341. Min Act: -0.1699
Data Index: 2940557 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 1691019 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1699
Data Index: 1864361 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 93107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 8133043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 3016808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 4806443 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 2418216 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1699
Data Index: 7725586 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8153. Min Range: -4.8153
Max Act: 4.5028. Min Act: -0.1700
Data Index: 2083145 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19