Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5166 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1186. Min Range: -7.1186
Max Act: 7.1186. Min Act: -0.1700
Data Index: 1384468 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.9936. Min Act: -0.1700
Data Index: 7428338 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.9311. Min Act: -0.1700
Data Index: 6535470 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8999. Min Act: -0.1700
Data Index: 4413766 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8686. Min Act: -0.1700
Data Index: 4711697 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8686. Min Act: -0.1700
Data Index: 3691529 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8686. Min Act: -0.1700
Data Index: 4438096 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8374. Min Act: -0.1700
Data Index: 4688376 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.8061. Min Act: -0.1700
Data Index: 1703030 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.7749. Min Act: -0.1700
Data Index: 2312084 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.7124. Min Act: -0.1700
Data Index: 3219901 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.7124. Min Act: -0.1700
Data Index: 6716328 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.6499. Min Act: -0.1700
Data Index: 4081025 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.6186. Min Act: -0.1700
Data Index: 1071503 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.6186. Min Act: -0.1700
Data Index: 2756918 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.5874. Min Act: -0.1700
Data Index: 3031407 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.6186. Min Act: -0.1700
Data Index: 4210615 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.5874. Min Act: -0.1700
Data Index: 5627648 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.5561. Min Act: -0.1700
Data Index: 7566215 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1186. Min Range: -7.1186
Max Act: 6.5561. Min Act: -0.1700
Data Index: 4341573 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19