Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.5127. Min Act: -0.1700
Data Index: 7589188 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.5127. Min Act: -0.1700
Data Index: 6377376 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.4813. Min Act: -0.1700
Data Index: 2846292 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.4500. Min Act: -0.1700
Data Index: 4213437 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.4343. Min Act: -0.1700
Data Index: 924822 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.4030. Min Act: -0.1700
Data Index: 6854007 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3873. Min Act: -0.1700
Data Index: 1968785 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3873. Min Act: -0.1700
Data Index: 2933158 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3716. Min Act: -0.1700
Data Index: 5756444 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3089. Min Act: -0.1700
Data Index: 8532198 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3245. Min Act: -0.1700
Data Index: 7142733 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3245. Min Act: -0.1700
Data Index: 3022996 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3089. Min Act: -0.1700
Data Index: 5204110 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2932. Min Act: -0.1700
Data Index: 7115033 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2775. Min Act: -0.1700
Data Index: 2729922 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2460. Min Act: -0.1700
Data Index: 914439 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2617. Min Act: -0.1700
Data Index: 5015151 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2460. Min Act: -0.1700
Data Index: 929987 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2617. Min Act: -0.1700
Data Index: 128255 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2460. Min Act: -0.1700
Data Index: 6605447 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19