Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6900. Min Act: -0.1700
Data Index: 5493541 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6379. Min Act: -0.1700
Data Index: 4886389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6291. Min Act: -0.1700
Data Index: 6771032 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6030. Min Act: -0.1700
Data Index: 477262 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6030. Min Act: -0.1700
Data Index: 6149511 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5768. Min Act: -0.1700
Data Index: 8418841 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.6030. Min Act: -0.1700
Data Index: 6842515 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5942. Min Act: -0.1700
Data Index: 7035566 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5768. Min Act: -0.1699
Data Index: 2052047 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5768. Min Act: -0.1700
Data Index: 1801043 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5593. Min Act: -0.1700
Data Index: 3048337 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5680. Min Act: -0.1700
Data Index: 4040430 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5593. Min Act: -0.1700
Data Index: 6160492 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5593. Min Act: -0.1700
Data Index: 8034291 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5505. Min Act: -0.1700
Data Index: 7143674 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5418. Min Act: -0.1700
Data Index: 3216531 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5593. Min Act: -0.1700
Data Index: 5623381 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5505. Min Act: -0.1700
Data Index: 6129579 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5418. Min Act: -0.1682
Data Index: 6733152 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6900. Min Range: -1.6900
Max Act: 1.5505. Min Act: -0.1700
Data Index: 669625 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19