Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.9752. Min Act: -0.1700
Data Index: 1522742 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0064. Min Range: -5.0064
Max Act: 5.0064. Min Act: -0.1700
Data Index: 289972 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.9439. Min Act: -0.1700
Data Index: 3832862 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.9439. Min Act: -0.1700
Data Index: 8803064 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.9127. Min Act: -0.1700
Data Index: 8521622 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.8814. Min Act: -0.1700
Data Index: 8185532 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.9127. Min Act: -0.1700
Data Index: 2027490 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.8814. Min Act: -0.1700
Data Index: 6775156 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.8502. Min Act: -0.1700
Data Index: 7936810 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.8189. Min Act: -0.1700
Data Index: 2356806 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.7877. Min Act: -0.1700
Data Index: 2146763 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.7252. Min Act: -0.1700
Data Index: 5971544 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.7252. Min Act: -0.1700
Data Index: 110921 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6939. Min Act: -0.1700
Data Index: 1496411 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6939. Min Act: -0.1700
Data Index: 2555685 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6939. Min Act: -0.1700
Data Index: 4270690 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6627. Min Act: -0.1700
Data Index: 6017330 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6627. Min Act: -0.1700
Data Index: 114876 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6002. Min Act: -0.1700
Data Index: 4938590 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0064. Min Range: -5.0064
Max Act: 4.6314. Min Act: -0.1700
Data Index: 318867 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19