Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.4569. Min Act: -0.1700
Data Index: 6213141 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3944. Min Act: -0.1700
Data Index: 2534633 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.1444. Min Act: -0.1700
Data Index: 1183536 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.1131. Min Act: -0.1700
Data Index: 7001937 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.0194. Min Act: -0.1700
Data Index: 337243 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.9881. Min Act: -0.1700
Data Index: 4571132 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.9569. Min Act: -0.1700
Data Index: 356113 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.9256. Min Act: -0.1700
Data Index: 5015096 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8944. Min Act: -0.1700
Data Index: 1191414 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.9256. Min Act: -0.1700
Data Index: 7367395 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8944. Min Act: -0.1700
Data Index: 7436458 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8944. Min Act: -0.1700
Data Index: 7487359 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8631. Min Act: -0.1700
Data Index: 6943372 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8631. Min Act: -0.1700
Data Index: 7757518 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8319. Min Act: -0.1700
Data Index: 956030 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8319. Min Act: -0.1700
Data Index: 992793 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8006. Min Act: -0.1700
Data Index: 4909111 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8006. Min Act: -0.1700
Data Index: 6740938 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8006. Min Act: -0.1700
Data Index: 946418 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4569. Min Range: -5.4569
Max Act: 4.8006. Min Act: -0.1700
Data Index: 620080 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19