Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6108 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.2499. Min Act: -0.1700
Data Index: 692041 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1874. Min Act: -0.1700
Data Index: 639591 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1874. Min Act: -0.1700
Data Index: 4649405 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1561. Min Act: -0.1700
Data Index: 6409700 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1561. Min Act: -0.1700
Data Index: 8320981 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1249. Min Act: -0.1700
Data Index: 8219214 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.1249. Min Act: -0.1700
Data Index: 7127971 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.0624. Min Act: -0.1700
Data Index: 7270160 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2499. Min Range: -5.2499
Max Act: 5.0624. Min Act: -0.1700
Data Index: 1331293 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9999. Min Act: -0.1700
Data Index: 4921565 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9686. Min Act: -0.1700
Data Index: 3541809 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9686. Min Act: -0.1700
Data Index: 7456526 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9999. Min Act: -0.1700
Data Index: 20736 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9374. Min Act: -0.1700
Data Index: 7352971 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9374. Min Act: -0.1700
Data Index: 1839286 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9374. Min Act: -0.1700
Data Index: 8316816 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9374. Min Act: -0.1700
Data Index: 7571124 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9061. Min Act: -0.1700
Data Index: 1113480 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9061. Min Act: -0.1700
Data Index: 4513163 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2499. Min Range: -5.2499
Max Act: 4.9061. Min Act: -0.1700
Data Index: 977882 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19