Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1575 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0694. Min Range: -5.0694
Max Act: 5.0694. Min Act: -0.1700
Data Index: 5905303 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.7569. Min Act: -0.1700
Data Index: 4908297 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.6006. Min Act: -0.1700
Data Index: 5248876 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.6006. Min Act: -0.1700
Data Index: 3361656 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5381. Min Act: -0.1700
Data Index: 813297 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5069. Min Act: -0.1700
Data Index: 4561927 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5381. Min Act: -0.1700
Data Index: 7079597 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5381. Min Act: -0.1700
Data Index: 4097117 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5381. Min Act: -0.1700
Data Index: 6807624 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.5069. Min Act: -0.1700
Data Index: 6807625 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4756. Min Act: -0.1700
Data Index: 5292903 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4444. Min Act: -0.1700
Data Index: 2878271 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4444. Min Act: -0.1700
Data Index: 2412615 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4756. Min Act: -0.1700
Data Index: 2878266 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4444. Min Act: -0.1700
Data Index: 4097121 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4131. Min Act: -0.1700
Data Index: 5356520 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4131. Min Act: -0.1700
Data Index: 2249005 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.4131. Min Act: -0.1700
Data Index: 2931433 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.3818. Min Act: -0.1700
Data Index: 4354352 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0694. Min Range: -5.0694
Max Act: 4.3506. Min Act: -0.1700
Data Index: 7392504 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19