Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4163 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3538. Min Range: -7.3538
Max Act: 7.3538. Min Act: -0.1700
Data Index: 2514292 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3538. Min Range: -7.3538
Max Act: 7.0413. Min Act: -0.1700
Data Index: 1756007 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3538. Min Range: -7.3538
Max Act: 7.0101. Min Act: -0.1700
Data Index: 5688208 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.9788. Min Act: -0.1700
Data Index: 2350769 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.9163. Min Act: -0.1700
Data Index: 108892 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3825929 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.8226. Min Act: -0.1700
Data Index: 4706062 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.7913. Min Act: -0.1700
Data Index: 6892943 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.7288. Min Act: -0.1700
Data Index: 3436833 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.7288. Min Act: -0.1700
Data Index: 8757461 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6976. Min Act: -0.1700
Data Index: 5805284 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6976. Min Act: -0.1700
Data Index: 5077143 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6976. Min Act: -0.1700
Data Index: 4109567 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6976. Min Act: -0.1700
Data Index: 8002098 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6663. Min Act: -0.1700
Data Index: 4265753 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6663. Min Act: -0.1700
Data Index: 2387671 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6351. Min Act: -0.1700
Data Index: 1354901 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6351. Min Act: -0.1700
Data Index: 2262695 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6351. Min Act: -0.1700
Data Index: 2139934 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3538. Min Range: -7.3538
Max Act: 6.6351. Min Act: -0.1700
Data Index: 7317384 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19