Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 798 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.6166. Min Act: -0.1700
Data Index: 1440977 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5540. Min Act: -0.1700
Data Index: 3960788 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5540. Min Act: -0.1700
Data Index: 1652882 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5227. Min Act: -0.1700
Data Index: 116641 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5227. Min Act: -0.1700
Data Index: 4475315 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5227. Min Act: -0.1700
Data Index: 1427353 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5227. Min Act: -0.1700
Data Index: 6761177 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4444. Min Act: -0.1700
Data Index: 8231347 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4757. Min Act: -0.1700
Data Index: 2781753 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 664531 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 6557518 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4444. Min Act: -0.1700
Data Index: 927565 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 5369018 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4444. Min Act: -0.1700
Data Index: 2888682 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 1286875 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 3668601 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4130. Min Act: -0.1700
Data Index: 3526490 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4130. Min Act: -0.1700
Data Index: 6652823 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3974. Min Act: -0.1700
Data Index: 3819663 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4287. Min Act: -0.1700
Data Index: 7920779 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19