Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5146850 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4981. Min Act: -0.1700
Data Index: 8625195 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4981. Min Act: -0.1700
Data Index: 112576 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4043. Min Act: -0.1700
Data Index: 8060934 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.3731. Min Act: -0.1700
Data Index: 6533167 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.3418. Min Act: -0.1700
Data Index: 572943 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4356. Min Act: -0.1700
Data Index: 3603484 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.3106. Min Act: -0.1700
Data Index: 2731948 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2793. Min Act: -0.1700
Data Index: 7264604 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2481. Min Act: -0.1700
Data Index: 5036017 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2481. Min Act: -0.1700
Data Index: 7678172 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2481. Min Act: -0.1700
Data Index: 2916294 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2168. Min Act: -0.1700
Data Index: 747461 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2168. Min Act: -0.1700
Data Index: 4653934 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2168. Min Act: -0.1700
Data Index: 2027962 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2168. Min Act: -0.1700
Data Index: 6575050 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1856. Min Act: -0.1700
Data Index: 5422294 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1543. Min Act: -0.1700
Data Index: 824810 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1856. Min Act: -0.1700
Data Index: 2937157 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1543. Min Act: -0.1700
Data Index: 4337773 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19