Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5601 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0882. Min Range: -8.0882
Max Act: 8.0882. Min Act: -0.1700
Data Index: 7868739 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.9632. Min Act: -0.1700
Data Index: 732540 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.7757. Min Act: -0.1700
Data Index: 8444764 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.7132. Min Act: -0.1700
Data Index: 8646457 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.6507. Min Act: -0.1700
Data Index: 3095930 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.6507. Min Act: -0.1700
Data Index: 7452026 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.6507. Min Act: -0.1700
Data Index: 7468233 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5882. Min Act: -0.1700
Data Index: 295257 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5882. Min Act: -0.1700
Data Index: 8277365 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5257. Min Act: -0.1700
Data Index: 8375433 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5257. Min Act: -0.1700
Data Index: 3768723 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5257. Min Act: -0.1700
Data Index: 5094018 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4944. Min Act: -0.1700
Data Index: 3822638 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.5257. Min Act: -0.1700
Data Index: 8098966 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4944. Min Act: -0.1700
Data Index: 6281123 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4632. Min Act: -0.1700
Data Index: 4312658 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4632. Min Act: -0.1700
Data Index: 3052019 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4632. Min Act: -0.1700
Data Index: 3423012 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4319. Min Act: -0.1700
Data Index: 5367771 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0882. Min Range: -8.0882
Max Act: 7.4632. Min Act: -0.1700
Data Index: 8048100 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19