Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.2330. Min Act: -0.1700
Data Index: 2757824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.2016. Min Act: -0.1700
Data Index: 3881788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1858. Min Act: -0.1700
Data Index: 6285067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1544. Min Act: -0.1700
Data Index: 6152923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1544. Min Act: -0.1700
Data Index: 1124245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1386. Min Act: -0.1700
Data Index: 7852808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 2072665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 3090624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 2266082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 5200001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 523432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 7305985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 7231581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 7124586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.1071. Min Act: -0.1700
Data Index: 4691475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.0914. Min Act: -0.1700
Data Index: 1250167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.0914. Min Act: -0.1700
Data Index: 6974514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.0756. Min Act: -0.1700
Data Index: 6410157 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.0914. Min Act: -0.1700
Data Index: 217149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2330. Min Range: -3.2330
Max Act: 3.0914. Min Act: -0.1700
Data Index: 3746717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19