Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.9464. Min Act: -0.1700
Data Index: 4189984 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.6652. Min Act: -0.1700
Data Index: 7982690 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.6339. Min Act: -0.1700
Data Index: 4373934 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.6027. Min Act: -0.1700
Data Index: 4349218 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.4777. Min Act: -0.1700
Data Index: 2346346 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.4152. Min Act: -0.1700
Data Index: 6512183 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3839. Min Act: -0.1700
Data Index: 5414479 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3839. Min Act: -0.1700
Data Index: 577775 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3839. Min Act: -0.1700
Data Index: 938236 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3527. Min Act: -0.1700
Data Index: 5950771 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3214. Min Act: -0.1700
Data Index: 3481263 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.3214. Min Act: -0.1700
Data Index: 120326 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2902. Min Act: -0.1700
Data Index: 3468473 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2902. Min Act: -0.1700
Data Index: 286666 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2902. Min Act: -0.1700
Data Index: 649806 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2589. Min Act: -0.1700
Data Index: 3665770 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2589. Min Act: -0.1700
Data Index: 5941706 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2589. Min Act: -0.1700
Data Index: 593427 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2277. Min Act: -0.1700
Data Index: 7139155 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9464. Min Range: -7.9464
Max Act: 7.2277. Min Act: -0.1700
Data Index: 1516733 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19