Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3123. Min Range: -9.3123
Max Act: 9.3123. Min Act: -0.1700
Data Index: 1388265 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.9373. Min Act: -0.1700
Data Index: 3187338 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.7498. Min Act: -0.1700
Data Index: 6722051 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.8123. Min Act: -0.1700
Data Index: 1350501 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.7498. Min Act: -0.1700
Data Index: 3191333 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.7498. Min Act: -0.1700
Data Index: 7825154 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.6248. Min Act: -0.1700
Data Index: 3868402 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.4998. Min Act: -0.1700
Data Index: 2502073 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.4373. Min Act: -0.1700
Data Index: 6893516 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.4373. Min Act: -0.1700
Data Index: 3037033 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.4373. Min Act: -0.1700
Data Index: 8604432 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.4373. Min Act: -0.1700
Data Index: 8067514 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.3748. Min Act: -0.1700
Data Index: 3088127 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.3123. Min Act: -0.1700
Data Index: 3189321 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.3123. Min Act: -0.1700
Data Index: 7863708 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.2498. Min Act: -0.1700
Data Index: 5232383 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.2498. Min Act: -0.1700
Data Index: 1852608 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.3123. Min Act: -0.1700
Data Index: 210894 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.1873. Min Act: -0.1700
Data Index: 2711047 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3123. Min Range: -9.3123
Max Act: 8.1873. Min Act: -0.1700
Data Index: 2888779 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19