Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4162 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.1381. Min Act: -0.1700
Data Index: 8351202 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.1068. Min Act: -0.1700
Data Index: 5881696 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0756. Min Act: -0.1700
Data Index: 6101926 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.1068. Min Act: -0.1700
Data Index: 5676424 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 8351199 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 2934705 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 5189019 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 8528736 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 781110 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0131. Min Act: -0.1700
Data Index: 5334038 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0131. Min Act: -0.1700
Data Index: 8560805 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0131. Min Act: -0.1700
Data Index: 3325825 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 3833947 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0443. Min Act: -0.1700
Data Index: 6234728 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0131. Min Act: -0.1700
Data Index: 1783916 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1381. Min Range: -5.1381
Max Act: 5.0131. Min Act: -0.1700
Data Index: 7046020 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1381. Min Range: -5.1381
Max Act: 4.9818. Min Act: -0.1700
Data Index: 459290 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1381. Min Range: -5.1381
Max Act: 4.9818. Min Act: -0.1700
Data Index: 5676433 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1381. Min Range: -5.1381
Max Act: 4.9818. Min Act: -0.1700
Data Index: 675986 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1381. Min Range: -5.1381
Max Act: 4.9818. Min Act: -0.1700
Data Index: 7029347 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19