Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.9351. Min Act: -0.1700
Data Index: 8149762 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.8100. Min Act: -0.1700
Data Index: 3151495 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7787. Min Act: -0.1700
Data Index: 542471 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7474. Min Act: -0.1700
Data Index: 4600407 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7318. Min Act: -0.1700
Data Index: 562314 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7318. Min Act: -0.1700
Data Index: 2111579 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7161. Min Act: -0.1700
Data Index: 6677297 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7161. Min Act: -0.1700
Data Index: 8429367 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7161. Min Act: -0.1700
Data Index: 7813234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7161. Min Act: -0.1700
Data Index: 1994279 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7318. Min Act: -0.1700
Data Index: 250395 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7005. Min Act: -0.1700
Data Index: 8696598 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.7005. Min Act: -0.1700
Data Index: 776897 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6849. Min Act: -0.1700
Data Index: 2451355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6692. Min Act: -0.1700
Data Index: 8450918 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6536. Min Act: -0.1700
Data Index: 6914313 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6379. Min Act: -0.1700
Data Index: 7817996 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6379. Min Act: -0.1700
Data Index: 5206446 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6379. Min Act: -0.1700
Data Index: 854353 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9351. Min Range: -3.9351
Max Act: 3.6379. Min Act: -0.1700
Data Index: 7486481 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19