Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0310. Min Range: -6.0310
Max Act: 6.0310. Min Act: -0.1700
Data Index: 409510 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.9997. Min Act: -0.1700
Data Index: 7587393 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7810. Min Act: -0.1700
Data Index: 7101239 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7497. Min Act: -0.1700
Data Index: 37276 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7497. Min Act: -0.1700
Data Index: 2178894 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7497. Min Act: -0.1700
Data Index: 122900 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7497. Min Act: -0.1700
Data Index: 7132492 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.7185. Min Act: -0.1700
Data Index: 4319907 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6872. Min Act: -0.1700
Data Index: 2128819 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6872. Min Act: -0.1700
Data Index: 2948559 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4866776 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6560. Min Act: -0.1700
Data Index: 8739534 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6560. Min Act: -0.1700
Data Index: 449681 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6560. Min Act: -0.1700
Data Index: 575914 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6247. Min Act: -0.1700
Data Index: 4565572 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6247. Min Act: -0.1700
Data Index: 240034 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.5935. Min Act: -0.1700
Data Index: 1927323 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6247. Min Act: -0.1700
Data Index: 3118787 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6247. Min Act: -0.1700
Data Index: 2605267 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0310. Min Range: -6.0310
Max Act: 5.6247. Min Act: -0.1700
Data Index: 33687 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19