Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3756 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.3015. Min Act: -0.1700
Data Index: 7403127 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.2702. Min Act: -0.1700
Data Index: 5911754 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.3015. Min Act: -0.1700
Data Index: 5499336 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.2702. Min Act: -0.1700
Data Index: 1165194 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.2077. Min Act: -0.1700
Data Index: 5089183 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1765. Min Act: -0.1700
Data Index: 8577301 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1765. Min Act: -0.1700
Data Index: 2749722 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1452. Min Act: -0.1700
Data Index: 123388 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1452. Min Act: -0.1700
Data Index: 1682772 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1765. Min Act: -0.1700
Data Index: 7871154 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1452. Min Act: -0.1700
Data Index: 1454313 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1452. Min Act: -0.1700
Data Index: 1936851 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1452. Min Act: -0.1700
Data Index: 821498 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.0827. Min Act: -0.1700
Data Index: 2657738 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1140. Min Act: -0.1700
Data Index: 4653197 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1167518 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1140. Min Act: -0.1700
Data Index: 156751 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.1140. Min Act: -0.1700
Data Index: 7467227 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.0827. Min Act: -0.1700
Data Index: 7257873 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3015. Min Range: -4.3015
Max Act: 4.0827. Min Act: -0.1700
Data Index: 5858113 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19