Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5449 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.9131. Min Act: -0.1700
Data Index: 1628140 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7880. Min Act: -0.1700
Data Index: 8688112 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.8037. Min Act: -0.1700
Data Index: 5209464 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7880. Min Act: -0.1700
Data Index: 8200788 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7724. Min Act: -0.1700
Data Index: 5249765 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7568. Min Act: -0.1700
Data Index: 148503 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7411. Min Act: -0.1700
Data Index: 7421700 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7411. Min Act: -0.1700
Data Index: 6342284 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7255. Min Act: -0.1700
Data Index: 5204202 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7255. Min Act: -0.1700
Data Index: 5236685 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7255. Min Act: -0.1700
Data Index: 3110559 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7255. Min Act: -0.1700
Data Index: 29640 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7098. Min Act: -0.1700
Data Index: 1368172 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.7255. Min Act: -0.1700
Data Index: 4668049 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6942. Min Act: -0.1700
Data Index: 598554 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6942. Min Act: -0.1700
Data Index: 657563 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6785. Min Act: -0.1700
Data Index: 6798451 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6942. Min Act: -0.1700
Data Index: 4399713 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6785. Min Act: -0.1700
Data Index: 2118303 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9131. Min Range: -3.9131
Max Act: 3.6629. Min Act: -0.1700
Data Index: 5752451 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19