Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.6606. Min Act: -0.1700
Data Index: 6612932 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.2856. Min Act: -0.1700
Data Index: 4429706 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.2231. Min Act: -0.1700
Data Index: 2716421 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.1606. Min Act: -0.1700
Data Index: 5088576 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.1293. Min Act: -0.1700
Data Index: 3500064 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0668. Min Act: -0.1700
Data Index: 1718035 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0668. Min Act: -0.1700
Data Index: 6833989 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0356. Min Act: -0.1700
Data Index: 8229146 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3664737 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0043. Min Act: -0.1700
Data Index: 397462 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6606. Min Range: -5.6606
Max Act: 5.0043. Min Act: -0.1700
Data Index: 4236032 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9731. Min Act: -0.1700
Data Index: 1186684 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9731. Min Act: -0.1700
Data Index: 839303 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 1141952 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 6437133 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 7435850 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 2735519 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9106. Min Act: -0.1700
Data Index: 3367673 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7931284 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6606. Min Range: -5.6606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 491139 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19