Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4549 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1388. Min Range: -8.1388
Max Act: 8.1388. Min Act: -0.1700
Data Index: 7838085 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.8263. Min Act: -0.1700
Data Index: 4064035 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.7326. Min Act: -0.1700
Data Index: 2223828 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.6701. Min Act: -0.1700
Data Index: 6109430 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.6388. Min Act: -0.1700
Data Index: 856342 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.6076. Min Act: -0.1700
Data Index: 1970516 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.5451. Min Act: -0.1700
Data Index: 1982206 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.5451. Min Act: -0.1700
Data Index: 5993301 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.5138. Min Act: -0.1700
Data Index: 6606645 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4513. Min Act: -0.1700
Data Index: 6750291 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4826. Min Act: -0.1700
Data Index: 3409544 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4826. Min Act: -0.1700
Data Index: 7701210 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4513. Min Act: -0.1700
Data Index: 8172006 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4513. Min Act: -0.1700
Data Index: 4345635 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4201. Min Act: -0.1700
Data Index: 6276894 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4201. Min Act: -0.1700
Data Index: 2707938 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.4201. Min Act: -0.1700
Data Index: 3870018 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.3888. Min Act: -0.1700
Data Index: 5328020 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.3888. Min Act: -0.1700
Data Index: 1199964 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1388. Min Range: -8.1388
Max Act: 7.3888. Min Act: -0.1700
Data Index: 8148654 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19