Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1157 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.1491. Min Act: -0.1693
Data Index: 1186159 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 3455295 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.3991. Min Act: -0.1699
Data Index: 8799198 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.3366. Min Act: -0.1700
Data Index: 1526221 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.3366. Min Act: -0.1700
Data Index: 1256948 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.1491. Min Act: -0.1700
Data Index: 1258537 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.2741. Min Act: -0.1696
Data Index: 2428398 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.0866. Min Act: -0.1700
Data Index: 8551596 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5241. Min Range: -9.5241
Max Act: 7.2741. Min Act: -0.1700
Data Index: 8063636 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.5241. Min Act: -0.1700
Data Index: 1223903 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.0241. Min Act: -0.1692
Data Index: 3002599 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5241. Min Range: -9.5241
Max Act: 7.1491. Min Act: -0.1699
Data Index: 2602990 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.3991. Min Act: -0.1699
Data Index: 3065607 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.5241. Min Act: -0.1700
Data Index: 1693750 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.7741. Min Act: -0.1698
Data Index: 6309926 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5241. Min Range: -9.5241
Max Act: 6.8366. Min Act: -0.1700
Data Index: 181870 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5241. Min Range: -9.5241
Max Act: 7.6803. Min Act: -0.1698
Data Index: 2288092 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.8991. Min Act: -0.1700
Data Index: 8398761 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5241. Min Range: -9.5241
Max Act: 9.0866. Min Act: -0.1700
Data Index: 3379290 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5241. Min Range: -9.5241
Max Act: 8.4616. Min Act: -0.1700
Data Index: 974726 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19