Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.4188. Min Act: -0.1700
Data Index: 2292160 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.3698. Min Act: -0.1700
Data Index: 2180068 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.3042. Min Act: -0.1700
Data Index: 7124847 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2713. Min Act: -0.1700
Data Index: 210796 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2713. Min Act: -0.1700
Data Index: 1433760 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2713. Min Act: -0.1700
Data Index: 7780748 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2713. Min Act: -0.1700
Data Index: 4845071 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2547. Min Act: -0.1700
Data Index: 8175287 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2547. Min Act: -0.1700
Data Index: 6845286 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2547. Min Act: -0.1700
Data Index: 6449693 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2547. Min Act: -0.1700
Data Index: 8396424 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2217. Min Act: -0.1700
Data Index: 2942257 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2382. Min Act: -0.1700
Data Index: 588350 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2382. Min Act: -0.1700
Data Index: 6478702 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2382. Min Act: -0.1700
Data Index: 5435663 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2382. Min Act: -0.1700
Data Index: 8330227 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2382. Min Act: -0.1700
Data Index: 3020178 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2217. Min Act: -0.1700
Data Index: 147996 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2217. Min Act: -0.1700
Data Index: 147997 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4188. Min Range: -2.4188
Max Act: 2.2217. Min Act: -0.1700
Data Index: 481836 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19