Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 909297 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.3021. Min Act: -0.1700
Data Index: 4203005 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.2708. Min Act: -0.1700
Data Index: 7266330 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.2083. Min Act: -0.1700
Data Index: 7611658 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5643852 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.2083. Min Act: -0.1700
Data Index: 1232525 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.1458. Min Act: -0.1700
Data Index: 2512300 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.1146. Min Act: -0.1700
Data Index: 8609423 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.1458. Min Act: -0.1700
Data Index: 113659 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0833. Min Act: -0.1700
Data Index: 7322841 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.1146. Min Act: -0.1700
Data Index: 3199235 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0833. Min Act: -0.1700
Data Index: 3005857 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0833. Min Act: -0.1700
Data Index: 7181512 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0208. Min Act: -0.1700
Data Index: 5729102 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0833. Min Act: -0.1700
Data Index: 3561236 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 5374431 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 6155674 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0521. Min Act: -0.1700
Data Index: 6997244 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0208. Min Act: -0.1700
Data Index: 6851360 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3021. Min Range: -5.3021
Max Act: 5.0208. Min Act: -0.1700
Data Index: 2146311 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19