Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6372 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.4569. Min Act: -0.1700
Data Index: 6991905 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.3319. Min Act: -0.1700
Data Index: 8323078 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.2381. Min Act: -0.1700
Data Index: 8778288 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1756. Min Act: -0.1700
Data Index: 1379702 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1444. Min Act: -0.1700
Data Index: 5520634 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1131. Min Act: -0.1700
Data Index: 1616367 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1131. Min Act: -0.1700
Data Index: 4780596 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1444. Min Act: -0.1700
Data Index: 3709905 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1131. Min Act: -0.1700
Data Index: 5680370 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1131. Min Act: -0.1700
Data Index: 5556990 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.1131. Min Act: -0.1700
Data Index: 5981525 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1211733 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0818. Min Act: -0.1700
Data Index: 4319558 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3307294 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 8148373 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3360700 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 8090548 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 7248436 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3921420 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4569. Min Range: -4.4569
Max Act: 4.0506. Min Act: -0.1700
Data Index: 6424590 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19