Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6435294 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3571694 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.7706. Min Act: -0.1700
Data Index: 8067504 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.7081. Min Act: -0.1700
Data Index: 2323587 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.6769. Min Act: -0.1700
Data Index: 4215678 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.6456. Min Act: -0.1700
Data Index: 8600682 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.6144. Min Act: -0.1700
Data Index: 8415193 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.6144. Min Act: -0.1700
Data Index: 4200955 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 4882409 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5831. Min Act: -0.1700
Data Index: 754806 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5831. Min Act: -0.1700
Data Index: 2016036 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 2267636 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 8686350 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 2117250 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 5182754 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5831. Min Act: -0.1700
Data Index: 2212616 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5519. Min Act: -0.1700
Data Index: 6784689 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5831. Min Act: -0.1700
Data Index: 4375429 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5206. Min Act: -0.1700
Data Index: 109344 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7706. Min Range: -4.7706
Max Act: 4.5206. Min Act: -0.1700
Data Index: 154076 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19