Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.8319. Min Act: -0.1700
Data Index: 1808725 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.7069. Min Act: -0.1700
Data Index: 172913 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6756. Min Act: -0.1700
Data Index: 1714666 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.6131. Min Act: -0.1700
Data Index: 854493 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.5194. Min Act: -0.1700
Data Index: 2362555 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.5194. Min Act: -0.1700
Data Index: 6663239 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4881. Min Act: -0.1700
Data Index: 2087767 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.5194. Min Act: -0.1700
Data Index: 6063901 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4881. Min Act: -0.1700
Data Index: 7420237 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4569. Min Act: -0.1700
Data Index: 5820928 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4569. Min Act: -0.1700
Data Index: 6705024 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4569. Min Act: -0.1700
Data Index: 172911 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4256. Min Act: -0.1700
Data Index: 4046955 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4256. Min Act: -0.1700
Data Index: 5110212 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4256. Min Act: -0.1700
Data Index: 541599 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.4256. Min Act: -0.1700
Data Index: 5909266 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.3944. Min Act: -0.1700
Data Index: 3048208 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.3944. Min Act: -0.1700
Data Index: 5725739 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.3944. Min Act: -0.1700
Data Index: 7296323 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8319. Min Range: -4.8319
Max Act: 4.3944. Min Act: -0.1700
Data Index: 7038333 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19