Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1092. Min Range: -8.1092
Max Act: 8.1092. Min Act: -0.1700
Data Index: 705598 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.9530. Min Act: -0.1700
Data Index: 4756416 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.8592. Min Act: -0.1700
Data Index: 2923937 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.6405. Min Act: -0.1700
Data Index: 8227223 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.6405. Min Act: -0.1700
Data Index: 709955 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.5780. Min Act: -0.1700
Data Index: 709953 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.5155. Min Act: -0.1700
Data Index: 434440 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.5155. Min Act: -0.1700
Data Index: 709960 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.5467. Min Act: -0.1700
Data Index: 1785289 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.4842. Min Act: -0.1700
Data Index: 7784749 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.3592. Min Act: -0.1700
Data Index: 709956 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.3592. Min Act: -0.1700
Data Index: 8742116 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2967. Min Act: -0.1700
Data Index: 4756415 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2967. Min Act: -0.1700
Data Index: 8206153 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2655. Min Act: -0.1700
Data Index: 5380393 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2967. Min Act: -0.1700
Data Index: 8127847 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2342. Min Act: -0.1700
Data Index: 709962 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2655. Min Act: -0.1700
Data Index: 1639817 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2342. Min Act: -0.1700
Data Index: 1011706 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1092. Min Range: -8.1092
Max Act: 7.2342. Min Act: -0.1700
Data Index: 1785292 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19