Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4970. Min Act: -0.1700
Data Index: 2864365 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4970. Min Act: -0.1700
Data Index: 6978161 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4483. Min Act: -0.1700
Data Index: 2562302 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4646. Min Act: -0.1698
Data Index: 7624665 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4320. Min Act: -0.1700
Data Index: 5570656 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4320. Min Act: -0.1700
Data Index: 608077 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4320. Min Act: -0.1700
Data Index: 6610499 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4320. Min Act: -0.1676
Data Index: 2524131 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.4158. Min Act: -0.1700
Data Index: 2858000 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3831. Min Act: -0.1700
Data Index: 4328794 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3831. Min Act: -0.1700
Data Index: 2530146 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3668. Min Act: -0.1700
Data Index: 776358 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3668. Min Act: -0.1700
Data Index: 5851050 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3668. Min Act: -0.1700
Data Index: 1499877 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3668. Min Act: -0.1700
Data Index: 5129283 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3504. Min Act: -0.1700
Data Index: 401588 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3504. Min Act: -0.1700
Data Index: 677894 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3668. Min Act: -0.1694
Data Index: 4196420 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3504. Min Act: -0.1698
Data Index: 763769 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4970. Min Range: -2.4970
Max Act: 2.3340. Min Act: -0.1700
Data Index: 5269417 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19