Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 458 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.9202. Min Act: -0.1700
Data Index: 603395 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.7952. Min Act: -0.1700
Data Index: 5816529 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.8577. Min Act: -0.1700
Data Index: 8781769 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.7639. Min Act: -0.1700
Data Index: 5509007 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.7327. Min Act: -0.1700
Data Index: 2306383 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.6389. Min Act: -0.1700
Data Index: 3318971 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.6077. Min Act: -0.1700
Data Index: 543774 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.6389. Min Act: -0.1700
Data Index: 4698362 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5452. Min Act: -0.1700
Data Index: 800326 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5452. Min Act: -0.1700
Data Index: 2838074 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5452. Min Act: -0.1700
Data Index: 5740540 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5139. Min Act: -0.1700
Data Index: 2985215 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5139. Min Act: -0.1700
Data Index: 6716123 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.5139. Min Act: -0.1700
Data Index: 5829652 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4827. Min Act: -0.1700
Data Index: 5727519 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4827. Min Act: -0.1700
Data Index: 1883691 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4514. Min Act: -0.1700
Data Index: 882482 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4514. Min Act: -0.1700
Data Index: 3100679 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4514. Min Act: -0.1700
Data Index: 1676862 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9202. Min Range: -7.9202
Max Act: 7.4514. Min Act: -0.1700
Data Index: 7789517 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19