Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5155 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.8893. Min Act: -0.1700
Data Index: 4972222 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.8893. Min Act: -0.1700
Data Index: 4838735 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.8581. Min Act: -0.1700
Data Index: 2066366 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7955. Min Act: -0.1700
Data Index: 4434610 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 7875261 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 5115715 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 1237399 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 6780297 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 5500542 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 4529726 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7330. Min Act: -0.1700
Data Index: 2875522 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7330. Min Act: -0.1700
Data Index: 6780728 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7642. Min Act: -0.1700
Data Index: 332940 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7330. Min Act: -0.1700
Data Index: 7811471 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7017. Min Act: -0.1700
Data Index: 3786303 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7330. Min Act: -0.1700
Data Index: 3041156 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7017. Min Act: -0.1700
Data Index: 5579041 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7017. Min Act: -0.1700
Data Index: 4384727 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7017. Min Act: -0.1700
Data Index: 7318017 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7017. Min Act: -0.1700
Data Index: 948327 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19