Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4316416 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.4119. Min Act: -0.1700
Data Index: 4747086 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.3807. Min Act: -0.1700
Data Index: 1007479 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.3182. Min Act: -0.1700
Data Index: 5729327 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.2869. Min Act: -0.1700
Data Index: 8736653 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.2557. Min Act: -0.1700
Data Index: 8043002 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.1932. Min Act: -0.1700
Data Index: 3684326 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4300124 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0994. Min Act: -0.1700
Data Index: 4438444 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0682. Min Act: -0.1700
Data Index: 4737356 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0369. Min Act: -0.1700
Data Index: 168112 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0369. Min Act: -0.1700
Data Index: 5192239 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0057. Min Act: -0.1700
Data Index: 3354430 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4744. Min Range: -6.4744
Max Act: 6.0057. Min Act: -0.1700
Data Index: 1017782 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9744. Min Act: -0.1700
Data Index: 5943952 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9744. Min Act: -0.1700
Data Index: 155142 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9744. Min Act: -0.1700
Data Index: 1594591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9744. Min Act: -0.1700
Data Index: 7334762 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9119. Min Act: -0.1700
Data Index: 8070588 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4744. Min Range: -6.4744
Max Act: 5.9432. Min Act: -0.1700
Data Index: 7458808 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19