Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.4335. Min Act: -0.1700
Data Index: 4249136 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.4022. Min Act: -0.1700
Data Index: 8522338 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2772. Min Act: -0.1700
Data Index: 154830 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.3397. Min Act: -0.1700
Data Index: 6637890 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5206201 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2772. Min Act: -0.1700
Data Index: 8322762 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2460. Min Act: -0.1700
Data Index: 6486522 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2147. Min Act: -0.1700
Data Index: 8087865 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2147. Min Act: -0.1700
Data Index: 5421191 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.2147. Min Act: -0.1700
Data Index: 3185193 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1835. Min Act: -0.1700
Data Index: 7143348 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.0897. Min Act: -0.1700
Data Index: 6093515 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1522. Min Act: -0.1700
Data Index: 8074764 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1210. Min Act: -0.1700
Data Index: 6302320 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1522. Min Act: -0.1700
Data Index: 7889609 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1210. Min Act: -0.1700
Data Index: 6407836 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8497853 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.0585. Min Act: -0.1700
Data Index: 8013336 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.0585. Min Act: -0.1700
Data Index: 3462302 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4335. Min Range: -5.4335
Max Act: 5.0585. Min Act: -0.1700
Data Index: 4793153 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19