Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.7323. Min Act: -0.1700
Data Index: 6513625 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.7323. Min Act: -0.1700
Data Index: 49750 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.7010. Min Act: -0.1700
Data Index: 5072281 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2361412 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6385. Min Act: -0.1700
Data Index: 421123 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6698. Min Act: -0.1700
Data Index: 4096399 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6073. Min Act: -0.1700
Data Index: 4729637 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6385. Min Act: -0.1700
Data Index: 2664521 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6073. Min Act: -0.1700
Data Index: 8489215 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.5760. Min Act: -0.1700
Data Index: 7115649 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.6073. Min Act: -0.1700
Data Index: 7898765 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.5135. Min Act: -0.1700
Data Index: 5761972 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.5448. Min Act: -0.1700
Data Index: 4647401 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4510. Min Act: -0.1700
Data Index: 7205765 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4823. Min Act: -0.1700
Data Index: 7415191 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4823. Min Act: -0.1700
Data Index: 836667 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4510. Min Act: -0.1700
Data Index: 6323935 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4510. Min Act: -0.1700
Data Index: 4383672 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4823. Min Act: -0.1700
Data Index: 312924 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7323. Min Range: -5.7323
Max Act: 5.4823. Min Act: -0.1700
Data Index: 6336405 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19