Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.8344. Min Act: -0.1700
Data Index: 7019129 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.7093. Min Act: -0.1700
Data Index: 6024777 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 6503747 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6154. Min Act: -0.1700
Data Index: 1778891 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 8231259 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 5423463 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 3816894 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6154. Min Act: -0.1700
Data Index: 2096778 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6154. Min Act: -0.1700
Data Index: 498643 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5684. Min Act: -0.1700
Data Index: 5934035 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6154. Min Act: -0.1700
Data Index: 5883950 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5841. Min Act: -0.1700
Data Index: 1201876 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5841. Min Act: -0.1700
Data Index: 8308697 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5841. Min Act: -0.1700
Data Index: 385162 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5684. Min Act: -0.1700
Data Index: 949067 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5684. Min Act: -0.1700
Data Index: 7686248 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5528. Min Act: -0.1700
Data Index: 8327467 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5684. Min Act: -0.1700
Data Index: 4565473 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5684. Min Act: -0.1700
Data Index: 4678078 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5528. Min Act: -0.1700
Data Index: 491068 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19