Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0370. Min Range: -5.0370
Max Act: 5.0370. Min Act: -0.1700
Data Index: 8000134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.9432. Min Act: -0.1700
Data Index: 1177407 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.9120. Min Act: -0.1700
Data Index: 1745187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8495. Min Act: -0.1700
Data Index: 4210135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 2163250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 5274736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 2819205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 8049853 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8495. Min Act: -0.1700
Data Index: 6717593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 5314219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7870. Min Act: -0.1700
Data Index: 4955520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 5168806 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4711069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 2992580 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 3252239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 2157675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7870. Min Act: -0.1700
Data Index: 1881725 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4739658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 1498672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8182. Min Act: -0.1700
Data Index: 5289363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19