Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.2643. Min Act: -0.1700
Data Index: 3069091 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.2018. Min Act: -0.1700
Data Index: 5078452 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.2330. Min Act: -0.1700
Data Index: 7679585 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1705. Min Act: -0.1700
Data Index: 3400287 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1393. Min Act: -0.1700
Data Index: 6760036 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1393. Min Act: -0.1700
Data Index: 7731229 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1393. Min Act: -0.1700
Data Index: 2882353 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1393. Min Act: -0.1700
Data Index: 6577550 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1393. Min Act: -0.1700
Data Index: 6129916 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0768. Min Act: -0.1700
Data Index: 1222843 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1080. Min Act: -0.1700
Data Index: 1050919 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.1080. Min Act: -0.1700
Data Index: 2139767 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0455. Min Act: -0.1700
Data Index: 2046094 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0768. Min Act: -0.1700
Data Index: 4535513 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0455. Min Act: -0.1700
Data Index: 6805205 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0455. Min Act: -0.1700
Data Index: 2535434 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0455. Min Act: -0.1700
Data Index: 4516837 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0143. Min Act: -0.1700
Data Index: 2437026 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0143. Min Act: -0.1700
Data Index: 4444829 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2643. Min Range: -4.2643
Max Act: 4.0143. Min Act: -0.1700
Data Index: 2952730 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19