Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.2316. Min Act: -0.1700
Data Index: 7974010 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.1066. Min Act: -0.1700
Data Index: 4605010 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.1066. Min Act: -0.1700
Data Index: 6761259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.1066. Min Act: -0.1700
Data Index: 309118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.1066. Min Act: -0.1700
Data Index: 8157960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0753. Min Act: -0.1700
Data Index: 1099173 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0441. Min Act: -0.1700
Data Index: 559145 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0441. Min Act: -0.1700
Data Index: 6337117 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0441. Min Act: -0.1700
Data Index: 2899577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0128. Min Act: -0.1700
Data Index: 2317182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0128. Min Act: -0.1700
Data Index: 7528928 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0128. Min Act: -0.1700
Data Index: 6816348 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9816. Min Act: -0.1700
Data Index: 7401765 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9816. Min Act: -0.1700
Data Index: 5771944 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0128. Min Act: -0.1700
Data Index: 1914710 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2316. Min Range: -5.2316
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4916837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8054648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9816. Min Act: -0.1700
Data Index: 8056409 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9503. Min Act: -0.1700
Data Index: 4265732 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2316. Min Range: -5.2316
Max Act: 4.9503. Min Act: -0.1700
Data Index: 992384 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19