Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.2456. Min Act: -0.1699
Data Index: 6674647 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.2143. Min Act: -0.1700
Data Index: 5325226 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.1831. Min Act: -0.1700
Data Index: 3139422 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.0893. Min Act: -0.1699
Data Index: 3139425 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.1206. Min Act: -0.1700
Data Index: 6674650 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.0893. Min Act: -0.1695
Data Index: 3216960 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.0893. Min Act: -0.1698
Data Index: 6674648 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.0268. Min Act: -0.1535
Data Index: 1605445 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2456. Min Range: -8.2456
Max Act: 8.0268. Min Act: -0.1700
Data Index: 8148619 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.9956. Min Act: -0.1694
Data Index: 226986 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.9331. Min Act: -0.1700
Data Index: 1063448 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.9956. Min Act: -0.1685
Data Index: 189690 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.9643. Min Act: -0.1699
Data Index: 7649848 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.9331. Min Act: -0.1699
Data Index: 5325229 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.8706. Min Act: -0.1699
Data Index: 8562431 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.7768. Min Act: -0.1543
Data Index: 1605451 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.8081. Min Act: -0.1700
Data Index: 2284768 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.7456. Min Act: -0.1684
Data Index: 6583578 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.8081. Min Act: -0.1700
Data Index: 5955559 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2456. Min Range: -8.2456
Max Act: 7.7456. Min Act: -0.1700
Data Index: 4771539 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19