Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1660 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.7915. Min Act: -0.1700
Data Index: 7411471 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.6351. Min Act: -0.1700
Data Index: 7438343 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.6038. Min Act: -0.1700
Data Index: 7832891 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5882. Min Act: -0.1700
Data Index: 1568879 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5882. Min Act: -0.1700
Data Index: 3170725 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5882. Min Act: -0.1700
Data Index: 4350294 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5882. Min Act: -0.1700
Data Index: 5095009 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5882. Min Act: -0.1700
Data Index: 5834455 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5412. Min Act: -0.1700
Data Index: 5600167 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5568. Min Act: -0.1700
Data Index: 6810788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5568. Min Act: -0.1700
Data Index: 5325759 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5412. Min Act: -0.1700
Data Index: 860023 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5255. Min Act: -0.1700
Data Index: 7204257 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5255. Min Act: -0.1700
Data Index: 1548145 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5255. Min Act: -0.1700
Data Index: 8420384 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5255. Min Act: -0.1700
Data Index: 742679 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5412. Min Act: -0.1700
Data Index: 1247229 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.5255. Min Act: -0.1700
Data Index: 2879882 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.4785. Min Act: -0.1700
Data Index: 5440138 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7915. Min Range: -3.7915
Max Act: 3.4629. Min Act: -0.1700
Data Index: 5095010 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19