Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1975 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.4116. Min Act: -0.1700
Data Index: 3791824 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.3803. Min Act: -0.1700
Data Index: 7098240 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.3178. Min Act: -0.1700
Data Index: 7098248 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.3178. Min Act: -0.1700
Data Index: 7098252 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.0991. Min Act: -0.1700
Data Index: 4457461 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.0365. Min Act: -0.1700
Data Index: 5192262 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.0053. Min Act: -0.1700
Data Index: 6121647 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9740. Min Act: -0.1700
Data Index: 3020346 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9740. Min Act: -0.1700
Data Index: 2143621 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4116. Min Range: -4.4116
Max Act: 4.0053. Min Act: -0.1700
Data Index: 6843300 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9740. Min Act: -0.1700
Data Index: 3137513 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9428. Min Act: -0.1700
Data Index: 5065180 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9428. Min Act: -0.1700
Data Index: 876699 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9740. Min Act: -0.1700
Data Index: 1422011 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9115. Min Act: -0.1700
Data Index: 3857446 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.9115. Min Act: -0.1700
Data Index: 3150825 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.8490. Min Act: -0.1700
Data Index: 6566668 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.8490. Min Act: -0.1700
Data Index: 484653 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3037827 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4116. Min Range: -4.4116
Max Act: 3.8333. Min Act: -0.1700
Data Index: 1114699 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19