Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.4197. Min Act: -0.1700
Data Index: 6335407 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.1384. Min Act: -0.1700
Data Index: 5253023 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.1384. Min Act: -0.1700
Data Index: 1941738 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.1072. Min Act: -0.1700
Data Index: 5887108 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.0447. Min Act: -0.1700
Data Index: 7252467 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.0447. Min Act: -0.1700
Data Index: 3917690 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.0134. Min Act: -0.1700
Data Index: 1219403 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.0134. Min Act: -0.1700
Data Index: 1540337 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4197. Min Range: -4.4197
Max Act: 4.0134. Min Act: -0.1700
Data Index: 2384203 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9821. Min Act: -0.1700
Data Index: 2632051 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4841601 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4727497 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9509. Min Act: -0.1700
Data Index: 2427173 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9821. Min Act: -0.1700
Data Index: 2631240 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4381205 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9196. Min Act: -0.1700
Data Index: 1366619 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9196. Min Act: -0.1700
Data Index: 8594350 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9196. Min Act: -0.1700
Data Index: 1375967 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.9196. Min Act: -0.1700
Data Index: 1838328 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4197. Min Range: -4.4197
Max Act: 3.8883. Min Act: -0.1700
Data Index: 3988601 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19