Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1433 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1866. Min Range: -4.1866
Max Act: 4.1866. Min Act: -0.1684
Data Index: 5770345 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1866. Min Range: -4.1866
Max Act: 4.1554. Min Act: -0.1697
Data Index: 5770370 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1866. Min Range: -4.1866
Max Act: 4.1241. Min Act: -0.1695
Data Index: 1477587 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.9991. Min Act: -0.1682
Data Index: 2787129 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.9991. Min Act: -0.1643
Data Index: 4405951 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.9366. Min Act: -0.1659
Data Index: 4405944 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.9366. Min Act: -0.1699
Data Index: 5709352 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.9053. Min Act: -0.1677
Data Index: 4405940 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.8115. Min Act: -0.1699
Data Index: 5770348 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1689
Data Index: 5770356 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1699
Data Index: 5770365 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1695
Data Index: 4405948 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1700
Data Index: 5770346 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1696
Data Index: 3763313 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7490. Min Act: -0.1695
Data Index: 3763309 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7490. Min Act: -0.1690
Data Index: 5709360 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7802. Min Act: -0.1694
Data Index: 5770344 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7490. Min Act: -0.1648
Data Index: 5770354 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.7177. Min Act: -0.1698
Data Index: 5709315 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1866. Min Range: -4.1866
Max Act: 3.6864. Min Act: -0.1681
Data Index: 5770366 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19