Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6057 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1890. Min Range: -6.1890
Max Act: 6.1890. Min Act: -0.1700
Data Index: 8157545 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1890. Min Range: -6.1890
Max Act: 6.0327. Min Act: -0.1700
Data Index: 8657734 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.9390. Min Act: -0.1700
Data Index: 3688076 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.9390. Min Act: -0.1700
Data Index: 5793844 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1944985 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.8452. Min Act: -0.1700
Data Index: 7273345 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.8452. Min Act: -0.1700
Data Index: 4421407 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.7202. Min Act: -0.1700
Data Index: 3564996 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.7202. Min Act: -0.1700
Data Index: 4091110 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.6890. Min Act: -0.1700
Data Index: 6217098 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.6577. Min Act: -0.1700
Data Index: 6637007 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.6265. Min Act: -0.1700
Data Index: 1791062 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.6265. Min Act: -0.1700
Data Index: 2949868 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 3088077 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 5587822 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 160901 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5640. Min Act: -0.1700
Data Index: 7500035 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5640. Min Act: -0.1700
Data Index: 155321 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5327. Min Act: -0.1700
Data Index: 4671409 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1890. Min Range: -6.1890
Max Act: 5.5327. Min Act: -0.1700
Data Index: 3290182 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19