Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2208 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.9190. Min Act: -0.1700
Data Index: 3965737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.9190. Min Act: -0.1700
Data Index: 6820555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.8252. Min Act: -0.1700
Data Index: 2485863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.8252. Min Act: -0.1700
Data Index: 1532835 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.8252. Min Act: -0.1700
Data Index: 6156559 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.8252. Min Act: -0.1700
Data Index: 834292 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.8565. Min Act: -0.1700
Data Index: 4821906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7626. Min Act: -0.1700
Data Index: 1374933 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7626. Min Act: -0.1700
Data Index: 1514694 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7626. Min Act: -0.1700
Data Index: 3804080 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 3266374 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4013295 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 3052029 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 6361182 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 681290 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 797617 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7254030 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7511188 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 1063360 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9190. Min Range: -3.9190
Max Act: 3.7314. Min Act: -0.1700
Data Index: 3150274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19