Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2295. Min Range: -6.2295
Max Act: 6.2295. Min Act: -0.1700
Data Index: 6914555 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2295. Min Range: -6.2295
Max Act: 6.1982. Min Act: -0.1700
Data Index: 921640 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8857. Min Act: -0.1700
Data Index: 8728775 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8857. Min Act: -0.1700
Data Index: 5700379 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8857. Min Act: -0.1700
Data Index: 3787780 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8857. Min Act: -0.1700
Data Index: 779227 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8545. Min Act: -0.1700
Data Index: 6578370 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8232. Min Act: -0.1700
Data Index: 7161730 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.8232. Min Act: -0.1700
Data Index: 1721333 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7920. Min Act: -0.1700
Data Index: 8175573 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7920. Min Act: -0.1700
Data Index: 4744284 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7920. Min Act: -0.1700
Data Index: 1042256 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7607. Min Act: -0.1700
Data Index: 916450 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7607. Min Act: -0.1700
Data Index: 8049698 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.7295. Min Act: -0.1700
Data Index: 3643953 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.6982. Min Act: -0.1700
Data Index: 4897841 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.6982. Min Act: -0.1700
Data Index: 2652458 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7042942 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.6670. Min Act: -0.1700
Data Index: 423142 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2295. Min Range: -6.2295
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2700804 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19