Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4202 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.6702. Min Act: -0.1700
Data Index: 7739947 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.6389. Min Act: -0.1700
Data Index: 8139531 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.5764. Min Act: -0.1700
Data Index: 2407054 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7972362 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.5139. Min Act: -0.1700
Data Index: 8469280 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4514. Min Act: -0.1700
Data Index: 2420773 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4514. Min Act: -0.1700
Data Index: 8504719 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4827. Min Act: -0.1700
Data Index: 1513387 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4514. Min Act: -0.1700
Data Index: 915836 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7562199 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 1464200 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7908392 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7172551 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 4546720 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.4202. Min Act: -0.1700
Data Index: 15434 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.3889. Min Act: -0.1700
Data Index: 4751849 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.3889. Min Act: -0.1700
Data Index: 746434 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.3889. Min Act: -0.1700
Data Index: 6699308 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.3889. Min Act: -0.1700
Data Index: 1831852 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6702. Min Range: -5.6702
Max Act: 5.3889. Min Act: -0.1700
Data Index: 612832 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19