Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1106. Min Range: -5.1106
Max Act: 5.1106. Min Act: -0.1700
Data Index: 8830354 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1106. Min Range: -5.1106
Max Act: 5.0481. Min Act: -0.1700
Data Index: 1521512 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1106. Min Range: -5.1106
Max Act: 5.0168. Min Act: -0.1700
Data Index: 5740630 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1106. Min Range: -5.1106
Max Act: 5.0168. Min Act: -0.1700
Data Index: 3300111 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.9856. Min Act: -0.1700
Data Index: 5630546 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.9231. Min Act: -0.1700
Data Index: 7778654 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8918. Min Act: -0.1700
Data Index: 1642283 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.9231. Min Act: -0.1700
Data Index: 7825631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8918. Min Act: -0.1700
Data Index: 4939521 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8606. Min Act: -0.1700
Data Index: 2253471 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8606. Min Act: -0.1700
Data Index: 3263822 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8606. Min Act: -0.1700
Data Index: 6322300 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8918. Min Act: -0.1700
Data Index: 2829709 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8606. Min Act: -0.1700
Data Index: 3042952 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8293. Min Act: -0.1700
Data Index: 1161410 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8293. Min Act: -0.1700
Data Index: 6696300 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.8293. Min Act: -0.1700
Data Index: 7778655 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.7981. Min Act: -0.1700
Data Index: 4801534 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.7981. Min Act: -0.1700
Data Index: 4886538 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1106. Min Range: -5.1106
Max Act: 4.7981. Min Act: -0.1700
Data Index: 3884811 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19