Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.9324. Min Act: -0.1700
Data Index: 2449115 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.6199. Min Act: -0.1700
Data Index: 8527729 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.5261. Min Act: -0.1700
Data Index: 1777941 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.5261. Min Act: -0.1700
Data Index: 1651253 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.4636. Min Act: -0.1700
Data Index: 8001797 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.4011. Min Act: -0.1700
Data Index: 3332207 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.4324. Min Act: -0.1700
Data Index: 4531354 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.4324. Min Act: -0.1700
Data Index: 595162 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.4011. Min Act: -0.1700
Data Index: 595164 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3386. Min Act: -0.1700
Data Index: 2208772 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3386. Min Act: -0.1700
Data Index: 915337 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3386. Min Act: -0.1700
Data Index: 5079750 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3074. Min Act: -0.1700
Data Index: 4040841 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3074. Min Act: -0.1700
Data Index: 4214548 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.2761. Min Act: -0.1700
Data Index: 6374081 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.2761. Min Act: -0.1700
Data Index: 1014137 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.3074. Min Act: -0.1700
Data Index: 4728951 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.2761. Min Act: -0.1700
Data Index: 7870922 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.2136. Min Act: -0.1700
Data Index: 4446462 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9324. Min Range: -6.9324
Max Act: 6.2449. Min Act: -0.1700
Data Index: 152256 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19