Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1198. Min Range: -8.1198
Max Act: 8.1198. Min Act: -0.1700
Data Index: 5390073 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1198. Min Range: -8.1198
Max Act: 8.0260. Min Act: -0.1700
Data Index: 5711352 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.9635. Min Act: -0.1700
Data Index: 7564648 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.9635. Min Act: -0.1700
Data Index: 2875445 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.7760. Min Act: -0.1700
Data Index: 4144764 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.7760. Min Act: -0.1700
Data Index: 2662957 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.6198. Min Act: -0.1700
Data Index: 7564651 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.6198. Min Act: -0.1700
Data Index: 5031824 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.6198. Min Act: -0.1700
Data Index: 753431 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.4635. Min Act: -0.1700
Data Index: 7564650 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.4010. Min Act: -0.1700
Data Index: 5928599 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.3385. Min Act: -0.1700
Data Index: 6621031 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.3698. Min Act: -0.1700
Data Index: 2481786 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.3385. Min Act: -0.1700
Data Index: 8321498 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.3385. Min Act: -0.1700
Data Index: 2882871 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.3073. Min Act: -0.1700
Data Index: 3331131 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.2760. Min Act: -0.1700
Data Index: 3568199 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.2448. Min Act: -0.1700
Data Index: 7564649 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.1823. Min Act: -0.1700
Data Index: 4696707 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1198. Min Range: -8.1198
Max Act: 7.1823. Min Act: -0.1700
Data Index: 5390074 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19