Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1105 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.4907. Min Act: -0.1700
Data Index: 4015907 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.4282. Min Act: -0.1700
Data Index: 381116 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.4282. Min Act: -0.1700
Data Index: 4364040 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.3657. Min Act: -0.1700
Data Index: 4015895 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.3657. Min Act: -0.1700
Data Index: 4015906 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.3657. Min Act: -0.1700
Data Index: 7442140 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.3032. Min Act: -0.1700
Data Index: 1060592 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2719. Min Act: -0.1700
Data Index: 1536462 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.3032. Min Act: -0.1700
Data Index: 8193026 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2719. Min Act: -0.1700
Data Index: 4015892 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2407. Min Act: -0.1700
Data Index: 1031546 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2407. Min Act: -0.1700
Data Index: 381114 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2094. Min Act: -0.1700
Data Index: 381122 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2094. Min Act: -0.1700
Data Index: 5105075 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2407. Min Act: -0.1700
Data Index: 4364038 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2719. Min Act: -0.1700
Data Index: 5604335 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2719. Min Act: -0.1700
Data Index: 2576409 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2094. Min Act: -0.1700
Data Index: 1563653 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2094. Min Act: -0.1700
Data Index: 1031532 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4907. Min Range: -8.4907
Max Act: 8.2094. Min Act: -0.1700
Data Index: 4879136 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19