Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1610. Min Range: -5.1610
Max Act: 5.1610. Min Act: -0.1700
Data Index: 1096047 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1610. Min Range: -5.1610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 1265073 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1610. Min Range: -5.1610
Max Act: 5.0360. Min Act: -0.1700
Data Index: 7566960 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1610. Min Range: -5.1610
Max Act: 5.0672. Min Act: -0.1700
Data Index: 2385652 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1610. Min Range: -5.1610
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2952972 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.9110. Min Act: -0.1700
Data Index: 8553186 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.9422. Min Act: -0.1700
Data Index: 3831096 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.9110. Min Act: -0.1700
Data Index: 4790612 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8797. Min Act: -0.1700
Data Index: 3301461 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8523777 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8797. Min Act: -0.1700
Data Index: 5836264 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8797. Min Act: -0.1700
Data Index: 916085 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8172. Min Act: -0.1700
Data Index: 7377101 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8797. Min Act: -0.1700
Data Index: 7056052 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8797. Min Act: -0.1700
Data Index: 2656811 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8172. Min Act: -0.1700
Data Index: 3352197 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8172. Min Act: -0.1700
Data Index: 2760829 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.7860. Min Act: -0.1700
Data Index: 1324328 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.7860. Min Act: -0.1700
Data Index: 3287205 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1610. Min Range: -5.1610
Max Act: 4.8172. Min Act: -0.1700
Data Index: 4325569 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19