Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2192 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6834. Min Act: -0.1700
Data Index: 1073839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.7146. Min Act: -0.1700
Data Index: 3509271 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6521. Min Act: -0.1700
Data Index: 1026521 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6521. Min Act: -0.1700
Data Index: 1204448 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6834. Min Act: -0.1700
Data Index: 1685544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6521. Min Act: -0.1700
Data Index: 6255554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6209. Min Act: -0.1700
Data Index: 4876919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.6521. Min Act: -0.1700
Data Index: 8827017 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.5896. Min Act: -0.1700
Data Index: 4506506 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.5896. Min Act: -0.1700
Data Index: 2346176 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.5584. Min Act: -0.1700
Data Index: 4452431 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.5584. Min Act: -0.1700
Data Index: 5265496 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.5584. Min Act: -0.1700
Data Index: 4983996 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.4334. Min Act: -0.1700
Data Index: 6343229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.4334. Min Act: -0.1700
Data Index: 2235748 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.4021. Min Act: -0.1700
Data Index: 397776 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.3709. Min Act: -0.1700
Data Index: 4268590 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.3709. Min Act: -0.1700
Data Index: 6442668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.3709. Min Act: -0.1700
Data Index: 3467274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7146. Min Range: -5.7146
Max Act: 5.3084. Min Act: -0.1700
Data Index: 5590772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19