Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1737467 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6181. Min Act: -0.1700
Data Index: 3232447 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8666581 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5556. Min Act: -0.1700
Data Index: 6607581 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5556. Min Act: -0.1700
Data Index: 7430835 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 4779982 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4931. Min Act: -0.1700
Data Index: 5585649 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 3308514 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 134352 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5556. Min Act: -0.1700
Data Index: 8435223 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 3027970 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 3522819 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 1737472 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4931. Min Act: -0.1700
Data Index: 3061260 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 2658187 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 859993 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 4344709 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 848576 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4306. Min Act: -0.1700
Data Index: 7734949 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 662079 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19