Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.4488. Min Act: -0.1700
Data Index: 5980925 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.3863. Min Act: -0.1700
Data Index: 432287 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.2926. Min Act: -0.1700
Data Index: 2824731 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.1676. Min Act: -0.1700
Data Index: 2470971 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.1988. Min Act: -0.1700
Data Index: 571558 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.1363. Min Act: -0.1700
Data Index: 3141121 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0426. Min Act: -0.1700
Data Index: 3154203 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0426. Min Act: -0.1700
Data Index: 1286650 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0113. Min Act: -0.1700
Data Index: 4807821 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0113. Min Act: -0.1700
Data Index: 5711684 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0113. Min Act: -0.1700
Data Index: 582492 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4488. Min Range: -5.4488
Max Act: 5.0113. Min Act: -0.1700
Data Index: 4249510 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9488. Min Act: -0.1700
Data Index: 6952038 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9801. Min Act: -0.1700
Data Index: 6456673 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9801. Min Act: -0.1700
Data Index: 3396037 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9801. Min Act: -0.1700
Data Index: 2277007 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9801. Min Act: -0.1700
Data Index: 2229175 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9488. Min Act: -0.1700
Data Index: 3930580 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9488. Min Act: -0.1700
Data Index: 6555917 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4488. Min Range: -5.4488
Max Act: 4.9176. Min Act: -0.1700
Data Index: 2831663 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19