Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.9260. Min Act: -0.1700
Data Index: 5709135 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6914. Min Act: -0.1700
Data Index: 8081081 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6914. Min Act: -0.1700
Data Index: 8279835 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6445. Min Act: -0.1700
Data Index: 6374064 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6601. Min Act: -0.1700
Data Index: 7301461 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6288. Min Act: -0.1700
Data Index: 5414579 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6445. Min Act: -0.1700
Data Index: 7306699 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6288. Min Act: -0.1700
Data Index: 6512394 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.6288. Min Act: -0.1700
Data Index: 969970 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5975. Min Act: -0.1700
Data Index: 7868656 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5975. Min Act: -0.1700
Data Index: 7310838 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5662. Min Act: -0.1700
Data Index: 5802550 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5662. Min Act: -0.1700
Data Index: 5911236 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5506. Min Act: -0.1700
Data Index: 7641154 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5193. Min Act: -0.1700
Data Index: 3456033 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5349. Min Act: -0.1700
Data Index: 3127954 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5506. Min Act: -0.1700
Data Index: 8137744 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.5193. Min Act: -0.1700
Data Index: 6922893 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.4879. Min Act: -0.1700
Data Index: 3046971 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9260. Min Range: -3.9260
Max Act: 3.4879. Min Act: -0.1700
Data Index: 4237738 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19