Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.3093. Min Act: -0.1700
Data Index: 4825121 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.3093. Min Act: -0.1700
Data Index: 1403850 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6077428 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.2156. Min Act: -0.1700
Data Index: 897605 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.2156. Min Act: -0.1700
Data Index: 8484635 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1843. Min Act: -0.1700
Data Index: 1545157 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.2156. Min Act: -0.1700
Data Index: 2304620 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1843. Min Act: -0.1700
Data Index: 3026792 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1531. Min Act: -0.1700
Data Index: 5207186 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1843. Min Act: -0.1700
Data Index: 2424237 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3523938 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1831001 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1531. Min Act: -0.1700
Data Index: 4253242 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.0906. Min Act: -0.1700
Data Index: 5655862 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.0906. Min Act: -0.1700
Data Index: 3673834 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.1531. Min Act: -0.1700
Data Index: 1322915 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3093. Min Range: -5.3093
Max Act: 4.9968. Min Act: -0.1700
Data Index: 2906448 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.0593. Min Act: -0.1700
Data Index: 1111665 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.0593. Min Act: -0.1700
Data Index: 4618006 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3093. Min Range: -5.3093
Max Act: 5.0593. Min Act: -0.1700
Data Index: 4555180 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19