Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.8788. Min Act: -0.1700
Data Index: 2108145 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.7851. Min Act: -0.1700
Data Index: 4957423 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2484915 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.7538. Min Act: -0.1700
Data Index: 5554691 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.7226. Min Act: -0.1700
Data Index: 3948326 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.7226. Min Act: -0.1700
Data Index: 8809855 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6913. Min Act: -0.1700
Data Index: 3682650 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6913. Min Act: -0.1700
Data Index: 6867501 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6601. Min Act: -0.1700
Data Index: 4401555 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6601. Min Act: -0.1700
Data Index: 5592228 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6601. Min Act: -0.1700
Data Index: 3443193 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6288. Min Act: -0.1700
Data Index: 8075891 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6288. Min Act: -0.1700
Data Index: 7638799 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5976. Min Act: -0.1700
Data Index: 5020000 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.6288. Min Act: -0.1700
Data Index: 6290687 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5976. Min Act: -0.1700
Data Index: 2254360 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5976. Min Act: -0.1700
Data Index: 4821664 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5976. Min Act: -0.1700
Data Index: 1226237 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5976. Min Act: -0.1700
Data Index: 1855192 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8788. Min Range: -5.8788
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4453304 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19