Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.4214. Min Act: -0.1700
Data Index: 3459412 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.3901. Min Act: -0.1700
Data Index: 4083523 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.2651. Min Act: -0.1700
Data Index: 3566681 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.1714. Min Act: -0.1700
Data Index: 5782571 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.0776. Min Act: -0.1700
Data Index: 5504042 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4214. Min Range: -7.4214
Max Act: 7.0776. Min Act: -0.1700
Data Index: 8386990 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.9214. Min Act: -0.1700
Data Index: 3420502 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8901. Min Act: -0.1700
Data Index: 5019587 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8589. Min Act: -0.1700
Data Index: 598308 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8276. Min Act: -0.1700
Data Index: 5631111 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8276. Min Act: -0.1700
Data Index: 4706152 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8276. Min Act: -0.1700
Data Index: 8224022 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1084241 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7964. Min Act: -0.1700
Data Index: 6880596 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7651. Min Act: -0.1700
Data Index: 1953793 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7651. Min Act: -0.1700
Data Index: 2925078 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7651. Min Act: -0.1700
Data Index: 3347277 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7651. Min Act: -0.1700
Data Index: 5934750 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7339. Min Act: -0.1700
Data Index: 7039673 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4214. Min Range: -7.4214
Max Act: 6.7339. Min Act: -0.1700
Data Index: 4280786 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19