Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4346 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.5402. Min Act: -0.1700
Data Index: 3825911 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.4777. Min Act: -0.1700
Data Index: 8034149 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.4464. Min Act: -0.1700
Data Index: 1839060 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.4777. Min Act: -0.1700
Data Index: 6952180 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3839. Min Act: -0.1700
Data Index: 4640112 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3527. Min Act: -0.1700
Data Index: 1486589 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3527. Min Act: -0.1700
Data Index: 732300 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4554148 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3214. Min Act: -0.1700
Data Index: 7492833 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3214. Min Act: -0.1700
Data Index: 5225254 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3214. Min Act: -0.1700
Data Index: 5215491 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3214. Min Act: -0.1700
Data Index: 3863393 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.3214. Min Act: -0.1700
Data Index: 8479414 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2589. Min Act: -0.1700
Data Index: 6152712 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2902. Min Act: -0.1700
Data Index: 6276638 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2589. Min Act: -0.1700
Data Index: 5119471 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2589. Min Act: -0.1700
Data Index: 1434333 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2589. Min Act: -0.1700
Data Index: 4216023 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.1964. Min Act: -0.1700
Data Index: 6743528 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5402. Min Range: -6.5402
Max Act: 6.2277. Min Act: -0.1700
Data Index: 3146656 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19