Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2782. Min Range: -7.2782
Max Act: 7.2782. Min Act: -0.1700
Data Index: 5742597 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2782. Min Range: -7.2782
Max Act: 7.0282. Min Act: -0.1700
Data Index: 79085 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.9657. Min Act: -0.1700
Data Index: 2700838 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.9345. Min Act: -0.1700
Data Index: 8519275 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.9657. Min Act: -0.1700
Data Index: 8353547 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.8407. Min Act: -0.1700
Data Index: 6746282 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.8720. Min Act: -0.1700
Data Index: 8652419 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.8720. Min Act: -0.1700
Data Index: 295401 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.7782. Min Act: -0.1700
Data Index: 704604 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.7470. Min Act: -0.1700
Data Index: 6746274 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.7157. Min Act: -0.1700
Data Index: 8327907 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.7470. Min Act: -0.1700
Data Index: 1695960 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6845. Min Act: -0.1700
Data Index: 5083268 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.7157. Min Act: -0.1700
Data Index: 8422374 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 1186407 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 4597832 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 8327910 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 1081701 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 7359355 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2782. Min Range: -7.2782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 2650134 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19