Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.8577. Min Act: -0.1700
Data Index: 383351 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.6390. Min Act: -0.1700
Data Index: 2181894 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.6077. Min Act: -0.1700
Data Index: 4410084 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5765. Min Act: -0.1700
Data Index: 7914216 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.5140. Min Act: -0.1700
Data Index: 2068803 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3890. Min Act: -0.1700
Data Index: 1261044 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3890. Min Act: -0.1700
Data Index: 7256118 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3265. Min Act: -0.1700
Data Index: 3813499 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.3265. Min Act: -0.1700
Data Index: 6638843 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2952. Min Act: -0.1700
Data Index: 5723090 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2640. Min Act: -0.1700
Data Index: 997168 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2640. Min Act: -0.1700
Data Index: 4495894 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 3157733 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 5708350 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2015. Min Act: -0.1700
Data Index: 3488843 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2015. Min Act: -0.1700
Data Index: 554119 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2015. Min Act: -0.1700
Data Index: 2384534 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2327. Min Act: -0.1700
Data Index: 7129008 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2015. Min Act: -0.1700
Data Index: 4134528 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8577. Min Range: -6.8577
Max Act: 6.2015. Min Act: -0.1700
Data Index: 4048399 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19