Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3657. Min Act: -0.1700
Data Index: 5742244 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3345. Min Act: -0.1700
Data Index: 1876392 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3345. Min Act: -0.1700
Data Index: 8535273 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.3345. Min Act: -0.1700
Data Index: 7012086 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2720. Min Act: -0.1700
Data Index: 97382 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2720. Min Act: -0.1700
Data Index: 2032258 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2720. Min Act: -0.1700
Data Index: 3736160 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2720. Min Act: -0.1700
Data Index: 2160705 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 2692291 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 6544456 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 3963221 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2407. Min Act: -0.1700
Data Index: 937710 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2095. Min Act: -0.1700
Data Index: 1003109 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2095. Min Act: -0.1700
Data Index: 1291189 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 6036690 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 7967073 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 4305068 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 6953996 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.1782. Min Act: -0.1700
Data Index: 1678315 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3657. Min Range: -4.3657
Max Act: 4.2095. Min Act: -0.1700
Data Index: 6148113 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19