Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2150. Min Range: -9.2150
Max Act: 9.2150. Min Act: -0.1700
Data Index: 4026359 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.9650. Min Act: -0.1700
Data Index: 6808066 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.9650. Min Act: -0.1700
Data Index: 2877124 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7775. Min Act: -0.1700
Data Index: 7460795 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7775. Min Act: -0.1700
Data Index: 4846077 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7150. Min Act: -0.1700
Data Index: 5351709 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7150. Min Act: -0.1700
Data Index: 8321874 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7150. Min Act: -0.1700
Data Index: 5874812 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.7150. Min Act: -0.1700
Data Index: 8054991 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.6525. Min Act: -0.1700
Data Index: 6184681 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.6525. Min Act: -0.1700
Data Index: 5643964 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.6525. Min Act: -0.1700
Data Index: 1194291 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.6525. Min Act: -0.1700
Data Index: 818889 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5900. Min Act: -0.1700
Data Index: 3592984 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5900. Min Act: -0.1700
Data Index: 8146292 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5900. Min Act: -0.1700
Data Index: 7943569 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5900. Min Act: -0.1700
Data Index: 1839306 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5900. Min Act: -0.1700
Data Index: 7930797 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.4650. Min Act: -0.1700
Data Index: 3517725 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2150. Min Range: -9.2150
Max Act: 8.5275. Min Act: -0.1700
Data Index: 2679878 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19