Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.4161. Min Act: -0.1700
Data Index: 2394754 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.1349. Min Act: -0.1700
Data Index: 6166952 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.0411. Min Act: -0.1700
Data Index: 6387520 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.0099. Min Act: -0.1700
Data Index: 4750588 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 8709945 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 586496 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 5636029 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9474. Min Act: -0.1700
Data Index: 5532740 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9474. Min Act: -0.1700
Data Index: 6494329 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9161. Min Act: -0.1700
Data Index: 1766906 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9161. Min Act: -0.1700
Data Index: 5333458 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8536. Min Act: -0.1700
Data Index: 2754129 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8536. Min Act: -0.1700
Data Index: 4968370 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 6334128 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 6761476 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 6312791 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8536. Min Act: -0.1700
Data Index: 6764110 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 3696424 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 6244777 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8224. Min Act: -0.1700
Data Index: 4533297 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19