Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 533 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.4535. Min Act: -0.1700
Data Index: 3935546 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.3910. Min Act: -0.1700
Data Index: 992263 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5821342 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6971231 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2972. Min Act: -0.1700
Data Index: 7667423 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5904278 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2972. Min Act: -0.1700
Data Index: 1278566 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.3285. Min Act: -0.1700
Data Index: 888813 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6534478 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2972. Min Act: -0.1700
Data Index: 2034935 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2660. Min Act: -0.1700
Data Index: 7999724 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2660. Min Act: -0.1700
Data Index: 7191167 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 1588757 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2660. Min Act: -0.1700
Data Index: 5699646 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2660. Min Act: -0.1700
Data Index: 4154424 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 2525843 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 4146924 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 3416481 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 2628552 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4535. Min Range: -5.4535
Max Act: 5.2347. Min Act: -0.1700
Data Index: 786602 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19