Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.6282. Min Act: -0.1700
Data Index: 7928297 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.5032. Min Act: -0.1700
Data Index: 2584423 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.4095. Min Act: -0.1700
Data Index: 972483 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.3157. Min Act: -0.1700
Data Index: 4454341 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2845. Min Act: -0.1700
Data Index: 5025523 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 3195026 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 3929790 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 1524977 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 4499772 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 7448432 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6291575 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3635754 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1907. Min Act: -0.1700
Data Index: 439233 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1595. Min Act: -0.1700
Data Index: 537573 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1595. Min Act: -0.1700
Data Index: 8062880 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1282. Min Act: -0.1700
Data Index: 4086453 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1595. Min Act: -0.1700
Data Index: 307103 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1282. Min Act: -0.1700
Data Index: 2867755 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.0970. Min Act: -0.1700
Data Index: 4852915 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6282. Min Range: -6.6282
Max Act: 6.1282. Min Act: -0.1700
Data Index: 1830959 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19