Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.7503. Min Act: -0.1700
Data Index: 8213647 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.7191. Min Act: -0.1700
Data Index: 4897437 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.6878. Min Act: -0.1700
Data Index: 934554 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.6566. Min Act: -0.1700
Data Index: 7018745 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.6253. Min Act: -0.1700
Data Index: 1431762 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.5941. Min Act: -0.1700
Data Index: 6765438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.5316. Min Act: -0.1700
Data Index: 2334975 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.4378. Min Act: -0.1700
Data Index: 1101455 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.4378. Min Act: -0.1700
Data Index: 2758947 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.4066. Min Act: -0.1700
Data Index: 883536 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.4066. Min Act: -0.1700
Data Index: 4449715 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3441. Min Act: -0.1700
Data Index: 4600910 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3441. Min Act: -0.1700
Data Index: 3881395 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3441. Min Act: -0.1700
Data Index: 893038 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3441. Min Act: -0.1700
Data Index: 7242326 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3128. Min Act: -0.1700
Data Index: 5094775 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3128. Min Act: -0.1700
Data Index: 4978175 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3128. Min Act: -0.1700
Data Index: 4733907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.2816. Min Act: -0.1700
Data Index: 4805763 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7503. Min Range: -5.7503
Max Act: 5.3128. Min Act: -0.1700
Data Index: 1489096 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19