Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0893. Min Range: -3.0893
Max Act: 3.0893. Min Act: -0.1700
Data Index: 8102095 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0893. Min Range: -3.0893
Max Act: 3.0420. Min Act: -0.1700
Data Index: 5055555 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9946. Min Act: -0.1700
Data Index: 1061311 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9788. Min Act: -0.1700
Data Index: 3324449 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9471. Min Act: -0.1700
Data Index: 6199685 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9471. Min Act: -0.1700
Data Index: 1706490 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9313. Min Act: -0.1700
Data Index: 4364147 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9313. Min Act: -0.1700
Data Index: 6111120 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9313. Min Act: -0.1700
Data Index: 6979699 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9471. Min Act: -0.1700
Data Index: 8281354 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9155. Min Act: -0.1700
Data Index: 3363028 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9313. Min Act: -0.1700
Data Index: 2799045 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8996. Min Act: -0.1700
Data Index: 1581286 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.9155. Min Act: -0.1700
Data Index: 3955214 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8996. Min Act: -0.1700
Data Index: 857296 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8996. Min Act: -0.1700
Data Index: 7579343 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8996. Min Act: -0.1700
Data Index: 7557179 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8679. Min Act: -0.1700
Data Index: 7034292 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8838. Min Act: -0.1700
Data Index: 3454567 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0893. Min Range: -3.0893
Max Act: 2.8679. Min Act: -0.1700
Data Index: 6041045 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19