Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.2140. Min Act: -0.1700
Data Index: 4853490 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.1827. Min Act: -0.1700
Data Index: 5768035 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0577. Min Act: -0.1700
Data Index: 1342073 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0577. Min Act: -0.1700
Data Index: 1214133 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0577. Min Act: -0.1700
Data Index: 3817187 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0577. Min Act: -0.1700
Data Index: 4002599 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 6626610 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0265. Min Act: -0.1700
Data Index: 2335168 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 585828 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0265. Min Act: -0.1700
Data Index: 535296 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0265. Min Act: -0.1700
Data Index: 565904 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0265. Min Act: -0.1700
Data Index: 3278011 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 1359906 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 3703284 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2140. Min Range: -6.2140
Max Act: 6.0265. Min Act: -0.1700
Data Index: 8494353 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 5010357 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9952. Min Act: -0.1700
Data Index: 2962694 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9640. Min Act: -0.1700
Data Index: 286900 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9640. Min Act: -0.1700
Data Index: 5187824 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2140. Min Range: -6.2140
Max Act: 5.9640. Min Act: -0.1700
Data Index: 5360035 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19