Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5588 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.9456. Min Act: -0.1700
Data Index: 1557612 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.7894. Min Act: -0.1700
Data Index: 4572575 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.6019. Min Act: -0.1700
Data Index: 900637 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.5081. Min Act: -0.1700
Data Index: 4640021 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.3519. Min Act: -0.1700
Data Index: 1149352 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.3519. Min Act: -0.1700
Data Index: 3107412 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.3206. Min Act: -0.1700
Data Index: 3106169 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2269. Min Act: -0.1700
Data Index: 8709363 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2581. Min Act: -0.1700
Data Index: 524644 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2581. Min Act: -0.1700
Data Index: 2526660 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2581. Min Act: -0.1700
Data Index: 3922329 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2581. Min Act: -0.1700
Data Index: 8240681 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2269. Min Act: -0.1700
Data Index: 6958590 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.2269. Min Act: -0.1700
Data Index: 8812074 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1956. Min Act: -0.1700
Data Index: 4869219 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1956. Min Act: -0.1700
Data Index: 6461059 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1331. Min Act: -0.1700
Data Index: 2041871 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1331. Min Act: -0.1700
Data Index: 2930055 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1331. Min Act: -0.1700
Data Index: 2973893 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9456. Min Range: -6.9456
Max Act: 6.1331. Min Act: -0.1700
Data Index: 5267369 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19