Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.9385. Min Act: -0.1700
Data Index: 1705587 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.9385. Min Act: -0.1700
Data Index: 2617851 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.8135. Min Act: -0.1700
Data Index: 69846 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.8448. Min Act: -0.1700
Data Index: 4973335 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.8448. Min Act: -0.1700
Data Index: 3596330 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7823. Min Act: -0.1700
Data Index: 1313307 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.8135. Min Act: -0.1700
Data Index: 8161575 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7823. Min Act: -0.1700
Data Index: 7983309 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7510. Min Act: -0.1700
Data Index: 1095434 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7198. Min Act: -0.1700
Data Index: 677572 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7198. Min Act: -0.1700
Data Index: 81750 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7198. Min Act: -0.1700
Data Index: 8498872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7510. Min Act: -0.1700
Data Index: 5066179 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7198. Min Act: -0.1700
Data Index: 8427344 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.7198. Min Act: -0.1700
Data Index: 7385392 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.6885. Min Act: -0.1700
Data Index: 4521158 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3422072 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.6573. Min Act: -0.1700
Data Index: 5238710 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.5948. Min Act: -0.1700
Data Index: 4712239 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.6260. Min Act: -0.1700
Data Index: 1995853 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19