Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0358. Min Range: -7.0358
Max Act: 7.0358. Min Act: -0.1700
Data Index: 2700801 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0358. Min Range: -7.0358
Max Act: 7.0358. Min Act: -0.1700
Data Index: 306478 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.9108. Min Act: -0.1700
Data Index: 8142293 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.9108. Min Act: -0.1700
Data Index: 6148894 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8483. Min Act: -0.1700
Data Index: 1703057 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8483. Min Act: -0.1700
Data Index: 3309078 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8483. Min Act: -0.1700
Data Index: 3428522 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8483. Min Act: -0.1700
Data Index: 8815037 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8483. Min Act: -0.1700
Data Index: 6578506 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8170. Min Act: -0.1700
Data Index: 5207689 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.8170. Min Act: -0.1700
Data Index: 8081690 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7858. Min Act: -0.1700
Data Index: 6168123 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7858. Min Act: -0.1700
Data Index: 407751 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7545. Min Act: -0.1700
Data Index: 469058 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7545. Min Act: -0.1700
Data Index: 4199673 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7545. Min Act: -0.1700
Data Index: 5951200 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7545. Min Act: -0.1700
Data Index: 4832158 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7545. Min Act: -0.1700
Data Index: 6867411 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7233. Min Act: -0.1700
Data Index: 669708 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0358. Min Range: -7.0358
Max Act: 6.7233. Min Act: -0.1700
Data Index: 6542401 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19