Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.9240. Min Act: -0.1700
Data Index: 7451669 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.8927. Min Act: -0.1700
Data Index: 4621243 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.8615. Min Act: -0.1700
Data Index: 1151176 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7989. Min Act: -0.1700
Data Index: 1433476 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7833. Min Act: -0.1700
Data Index: 3279762 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7989. Min Act: -0.1700
Data Index: 5643432 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7833. Min Act: -0.1700
Data Index: 3469078 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7520. Min Act: -0.1700
Data Index: 2413643 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7677. Min Act: -0.1700
Data Index: 5406695 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7520. Min Act: -0.1700
Data Index: 6980627 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7520. Min Act: -0.1700
Data Index: 3041239 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7207. Min Act: -0.1700
Data Index: 992033 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7364. Min Act: -0.1700
Data Index: 4824945 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7364. Min Act: -0.1700
Data Index: 2226245 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7051. Min Act: -0.1700
Data Index: 7318750 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7207. Min Act: -0.1700
Data Index: 1352029 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.6895. Min Act: -0.1700
Data Index: 2931689 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.7051. Min Act: -0.1700
Data Index: 6354640 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.6425. Min Act: -0.1700
Data Index: 3427331 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9240. Min Range: -3.9240
Max Act: 3.6895. Min Act: -0.1700
Data Index: 5971227 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19