Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.2520. Min Act: -0.1700
Data Index: 4144151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.1583. Min Act: -0.1700
Data Index: 6972527 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.1270. Min Act: -0.1700
Data Index: 768544 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0645. Min Act: -0.1700
Data Index: 768543 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0333. Min Act: -0.1700
Data Index: 8441110 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0333. Min Act: -0.1700
Data Index: 239920 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0333. Min Act: -0.1700
Data Index: 768539 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0333. Min Act: -0.1700
Data Index: 768545 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0333. Min Act: -0.1700
Data Index: 768542 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0020. Min Act: -0.1700
Data Index: 4148160 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2520. Min Range: -6.2520
Max Act: 6.0020. Min Act: -0.1700
Data Index: 970424 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 1482631 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9708. Min Act: -0.1700
Data Index: 5744128 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 768538 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9708. Min Act: -0.1700
Data Index: 7397231 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 2940838 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 5835604 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 4631387 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 5744129 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2520. Min Range: -6.2520
Max Act: 5.9395. Min Act: -0.1700
Data Index: 2940840 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19