Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.4261. Min Act: -0.1700
Data Index: 4448193 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3949. Min Act: -0.1700
Data Index: 4647335 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3324. Min Act: -0.1700
Data Index: 2233634 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3636. Min Act: -0.1700
Data Index: 6642287 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3324. Min Act: -0.1700
Data Index: 6478582 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3011. Min Act: -0.1700
Data Index: 1752347 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.3011. Min Act: -0.1699
Data Index: 5054437 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2386. Min Act: -0.1700
Data Index: 3493850 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2386. Min Act: -0.1700
Data Index: 5741732 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2386. Min Act: -0.1700
Data Index: 2544304 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.1761. Min Act: -0.1700
Data Index: 6987278 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 5418750 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 7392494 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 1287003 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 1972842 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3308661 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 8335016 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.1761. Min Act: -0.1700
Data Index: 6057357 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.2074. Min Act: -0.1700
Data Index: 1689220 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4261. Min Range: -5.4261
Max Act: 5.1761. Min Act: -0.1700
Data Index: 596130 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19