Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1878 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.6331. Min Act: -0.1700
Data Index: 2524232 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.4768. Min Act: -0.1700
Data Index: 7269063 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.4456. Min Act: -0.1700
Data Index: 6482549 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.4456. Min Act: -0.1700
Data Index: 6581100 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.4143. Min Act: -0.1700
Data Index: 5631120 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.3518. Min Act: -0.1700
Data Index: 4940293 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.3206. Min Act: -0.1700
Data Index: 5673101 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.2581. Min Act: -0.1700
Data Index: 4928107 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1956. Min Act: -0.1700
Data Index: 5613974 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.2268. Min Act: -0.1700
Data Index: 7294284 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1956. Min Act: -0.1700
Data Index: 2750707 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4489210 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1956. Min Act: -0.1700
Data Index: 7710393 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1956. Min Act: -0.1700
Data Index: 849387 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1643. Min Act: -0.1700
Data Index: 336317 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1643. Min Act: -0.1700
Data Index: 3300784 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1956. Min Act: -0.1700
Data Index: 2524235 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1331. Min Act: -0.1700
Data Index: 6217124 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1331. Min Act: -0.1700
Data Index: 830504 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6331. Min Range: -5.6331
Max Act: 5.1331. Min Act: -0.1700
Data Index: 6895848 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19