Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.4444. Min Act: -0.1700
Data Index: 7893425 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.4444. Min Act: -0.1700
Data Index: 6026197 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.4132. Min Act: -0.1700
Data Index: 5226729 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.3819. Min Act: -0.1700
Data Index: 5681012 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.3194. Min Act: -0.1700
Data Index: 2051917 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.3194. Min Act: -0.1700
Data Index: 8117222 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.3194. Min Act: -0.1700
Data Index: 6300965 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.3194. Min Act: -0.1700
Data Index: 3609664 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.2569. Min Act: -0.1700
Data Index: 6204888 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.2569. Min Act: -0.1700
Data Index: 6037170 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.2256. Min Act: -0.1700
Data Index: 8306387 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.2256. Min Act: -0.1700
Data Index: 7077748 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.2256. Min Act: -0.1700
Data Index: 7148934 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1944. Min Act: -0.1700
Data Index: 3609665 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1944. Min Act: -0.1700
Data Index: 66159 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1944. Min Act: -0.1700
Data Index: 4450245 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1631. Min Act: -0.1700
Data Index: 8614434 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1944. Min Act: -0.1700
Data Index: 7558140 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1631. Min Act: -0.1700
Data Index: 7482182 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4444. Min Range: -4.4444
Max Act: 4.1319. Min Act: -0.1700
Data Index: 2571367 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19