Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2290 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.8474. Min Act: -0.1700
Data Index: 5154127 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.6286. Min Act: -0.1700
Data Index: 7181337 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.5349. Min Act: -0.1700
Data Index: 6895065 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.4724. Min Act: -0.1700
Data Index: 8384388 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.4411. Min Act: -0.1700
Data Index: 6073398 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.4411. Min Act: -0.1700
Data Index: 2480726 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.3474. Min Act: -0.1700
Data Index: 2519620 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.3161. Min Act: -0.1700
Data Index: 2475966 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2849. Min Act: -0.1700
Data Index: 8262407 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2849. Min Act: -0.1700
Data Index: 8316476 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2536. Min Act: -0.1700
Data Index: 4241900 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2849. Min Act: -0.1700
Data Index: 1597581 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2224. Min Act: -0.1700
Data Index: 1155850 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2224. Min Act: -0.1700
Data Index: 3994734 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2224. Min Act: -0.1700
Data Index: 2555348 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2224. Min Act: -0.1700
Data Index: 3027379 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.2224. Min Act: -0.1700
Data Index: 4745565 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.1911. Min Act: -0.1700
Data Index: 6236189 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.1599. Min Act: -0.1700
Data Index: 5857591 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8474. Min Range: -7.8474
Max Act: 7.1286. Min Act: -0.1700
Data Index: 3186027 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19