Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5066 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0416. Min Range: -12.0416
Max Act: 12.0416. Min Act: -0.1700
Data Index: 581710 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.9166. Min Act: -0.1700
Data Index: 3302708 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.9166. Min Act: -0.1700
Data Index: 3480186 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.8541. Min Act: -0.1700
Data Index: 7810674 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.6666. Min Act: -0.1700
Data Index: 1328373 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.6041. Min Act: -0.1700
Data Index: 6910127 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.5416. Min Act: -0.1700
Data Index: 683594 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.4791. Min Act: -0.1700
Data Index: 238311 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.4791. Min Act: -0.1700
Data Index: 8649757 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.4166. Min Act: -0.1700
Data Index: 5049825 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.4166. Min Act: -0.1700
Data Index: 2891377 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.3541. Min Act: -0.1700
Data Index: 8678487 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.3541. Min Act: -0.1700
Data Index: 6178525 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.2916. Min Act: -0.1700
Data Index: 6634459 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.2916. Min Act: -0.1700
Data Index: 888245 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.2291. Min Act: -0.1700
Data Index: 5426137 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.1041. Min Act: -0.1700
Data Index: 7018695 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.1041. Min Act: -0.1700
Data Index: 6412973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.0416. Min Act: -0.1700
Data Index: 2251398 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0416. Min Range: -12.0416
Max Act: 11.0416. Min Act: -0.1700
Data Index: 5388119 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19