Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5185 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.5167. Min Act: -0.1700
Data Index: 5101629 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.2355. Min Act: -0.1700
Data Index: 1212274 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.2042. Min Act: -0.1700
Data Index: 1155610 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.2042. Min Act: -0.1700
Data Index: 729968 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1730. Min Act: -0.1700
Data Index: 4008457 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1730. Min Act: -0.1700
Data Index: 3042703 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1417. Min Act: -0.1700
Data Index: 4691254 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1417. Min Act: -0.1700
Data Index: 4681724 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1105. Min Act: -0.1700
Data Index: 7314683 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1105. Min Act: -0.1700
Data Index: 6414638 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.1105. Min Act: -0.1700
Data Index: 7329352 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.0792. Min Act: -0.1700
Data Index: 5373506 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.0480. Min Act: -0.1700
Data Index: 980153 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.0792. Min Act: -0.1700
Data Index: 4451524 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5167. Min Range: -6.5167
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5801649 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5167. Min Range: -6.5167
Max Act: 5.9855. Min Act: -0.1700
Data Index: 6372087 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5167. Min Range: -6.5167
Max Act: 5.9855. Min Act: -0.1700
Data Index: 8657172 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5167. Min Range: -6.5167
Max Act: 5.9855. Min Act: -0.1700
Data Index: 1803003 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5167. Min Range: -6.5167
Max Act: 5.9855. Min Act: -0.1700
Data Index: 4240274 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5167. Min Range: -6.5167
Max Act: 5.9542. Min Act: -0.1700
Data Index: 433600 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19