Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2440 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.2360. Min Act: -0.1700
Data Index: 4533281 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.2360. Min Act: -0.1700
Data Index: 3503028 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.2360. Min Act: -0.1700
Data Index: 4475247 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.2360. Min Act: -0.1700
Data Index: 3259998 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1735. Min Act: -0.1700
Data Index: 8679413 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1735. Min Act: -0.1700
Data Index: 4333315 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1422. Min Act: -0.1700
Data Index: 4403049 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1422. Min Act: -0.1700
Data Index: 3599937 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1422. Min Act: -0.1700
Data Index: 794488 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1735. Min Act: -0.1700
Data Index: 2451237 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1422. Min Act: -0.1700
Data Index: 2457396 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1594120 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.1110. Min Act: -0.1700
Data Index: 5374454 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0797. Min Act: -0.1700
Data Index: 7850662 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0485. Min Act: -0.1700
Data Index: 1825636 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0485. Min Act: -0.1700
Data Index: 5129192 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0797. Min Act: -0.1700
Data Index: 18947 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0172. Min Act: -0.1700
Data Index: 751375 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0172. Min Act: -0.1700
Data Index: 909433 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2360. Min Range: -5.2360
Max Act: 5.0172. Min Act: -0.1700
Data Index: 651128 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19