Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.9794. Min Act: -0.1700
Data Index: 6504406 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.9477. Min Act: -0.1700
Data Index: 2393532 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.9002. Min Act: -0.1700
Data Index: 5796549 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8526. Min Act: -0.1700
Data Index: 5269033 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8685. Min Act: -0.1700
Data Index: 8288205 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8367. Min Act: -0.1700
Data Index: 1462615 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8367. Min Act: -0.1700
Data Index: 163605 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8367. Min Act: -0.1700
Data Index: 5911606 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8208. Min Act: -0.1700
Data Index: 2686597 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8049. Min Act: -0.1700
Data Index: 814480 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8049. Min Act: -0.1700
Data Index: 7488459 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8049. Min Act: -0.1700
Data Index: 6283324 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8049. Min Act: -0.1700
Data Index: 5015716 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.8049. Min Act: -0.1700
Data Index: 1295423 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7889. Min Act: -0.1700
Data Index: 3567849 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7889. Min Act: -0.1700
Data Index: 4704650 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7570. Min Act: -0.1700
Data Index: 4822896 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7730. Min Act: -0.1700
Data Index: 2806156 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7570. Min Act: -0.1700
Data Index: 4975405 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9794. Min Range: -2.9794
Max Act: 2.7570. Min Act: -0.1700
Data Index: 5246807 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19