Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1376. Min Range: -8.1376
Max Act: 8.1376. Min Act: -0.1700
Data Index: 6201235 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1376. Min Range: -8.1376
Max Act: 8.0751. Min Act: -0.1700
Data Index: 234299 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.7626. Min Act: -0.1700
Data Index: 7160988 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.7626. Min Act: -0.1700
Data Index: 317497 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.7001. Min Act: -0.1700
Data Index: 5981285 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.7001. Min Act: -0.1700
Data Index: 3326056 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.6064. Min Act: -0.1700
Data Index: 4659606 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5751. Min Act: -0.1700
Data Index: 3056844 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.6064. Min Act: -0.1700
Data Index: 7128249 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 4605597 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5439. Min Act: -0.1700
Data Index: 3778476 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5439. Min Act: -0.1700
Data Index: 7952196 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 8830186 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 5948909 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.5126. Min Act: -0.1700
Data Index: 4582926 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.4501. Min Act: -0.1700
Data Index: 8168901 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.4814. Min Act: -0.1700
Data Index: 575293 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.4501. Min Act: -0.1700
Data Index: 2468772 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.4814. Min Act: -0.1700
Data Index: 3778472 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1376. Min Range: -8.1376
Max Act: 7.4501. Min Act: -0.1700
Data Index: 5979701 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19