Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 183 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7804. Min Act: -0.1700
Data Index: 390921 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7491. Min Act: -0.1700
Data Index: 2564492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7491. Min Act: -0.1700
Data Index: 318453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.8116. Min Act: -0.1700
Data Index: 7045397 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7491. Min Act: -0.1700
Data Index: 4931784 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7804. Min Act: -0.1700
Data Index: 4964696 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6866. Min Act: -0.1700
Data Index: 6211523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6866. Min Act: -0.1700
Data Index: 4211197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6866. Min Act: -0.1700
Data Index: 6342360 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6866. Min Act: -0.1700
Data Index: 8664943 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6866. Min Act: -0.1700
Data Index: 7933829 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.7179. Min Act: -0.1700
Data Index: 7038902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1700
Data Index: 5010468 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1700
Data Index: 6886860 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1700
Data Index: 3455911 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1699
Data Index: 6751868 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1700
Data Index: 148621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6554. Min Act: -0.1700
Data Index: 6629351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.6241. Min Act: -0.1700
Data Index: 5140542 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8116. Min Range: -6.8116
Max Act: 6.5929. Min Act: -0.1700
Data Index: 909766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19