Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.4076. Min Act: -0.1700
Data Index: 1338277 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.3451. Min Act: -0.1700
Data Index: 7312394 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.3138. Min Act: -0.1700
Data Index: 5069766 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1338276 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.2201. Min Act: -0.1700
Data Index: 1975770 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1575. Min Act: -0.1700
Data Index: 6900349 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1575. Min Act: -0.1700
Data Index: 3907347 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1575. Min Act: -0.1700
Data Index: 4173776 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1263. Min Act: -0.1700
Data Index: 4158104 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1263. Min Act: -0.1700
Data Index: 6982203 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0950. Min Act: -0.1700
Data Index: 3123316 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0950. Min Act: -0.1700
Data Index: 6273863 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 4943416 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 4603589 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 779191 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 6545116 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 6353836 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0325. Min Act: -0.1700
Data Index: 734659 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0325. Min Act: -0.1700
Data Index: 5773095 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0325. Min Act: -0.1700
Data Index: 3493651 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19