Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.8571. Min Act: -0.1700
Data Index: 6009169 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.7321. Min Act: -0.1700
Data Index: 6779192 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.5758. Min Act: -0.1700
Data Index: 2590100 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.4508. Min Act: -0.1700
Data Index: 8156658 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.3883. Min Act: -0.1700
Data Index: 7945441 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.4196. Min Act: -0.1700
Data Index: 3798533 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.3883. Min Act: -0.1700
Data Index: 2704807 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2946. Min Act: -0.1700
Data Index: 4398181 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2946. Min Act: -0.1700
Data Index: 6399104 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2946. Min Act: -0.1700
Data Index: 58747 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2946. Min Act: -0.1700
Data Index: 1623003 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2633. Min Act: -0.1700
Data Index: 1743205 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2633. Min Act: -0.1700
Data Index: 856993 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2633. Min Act: -0.1700
Data Index: 2467542 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2321. Min Act: -0.1700
Data Index: 2794041 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2633. Min Act: -0.1700
Data Index: 6909171 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2321. Min Act: -0.1700
Data Index: 1835286 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2008. Min Act: -0.1700
Data Index: 4282464 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2321. Min Act: -0.1700
Data Index: 7376567 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8571. Min Range: -5.8571
Max Act: 5.2321. Min Act: -0.1700
Data Index: 7792168 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19