Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.5104. Min Act: -0.1700
Data Index: 4454592 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.4791. Min Act: -0.1700
Data Index: 1667885 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.4791. Min Act: -0.1700
Data Index: 7711406 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.4166. Min Act: -0.1700
Data Index: 4721758 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.3541. Min Act: -0.1700
Data Index: 2098874 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2916. Min Act: -0.1700
Data Index: 7565931 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2291. Min Act: -0.1700
Data Index: 254516 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1979. Min Act: -0.1700
Data Index: 784522 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.2291. Min Act: -0.1700
Data Index: 4525888 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1354. Min Act: -0.1700
Data Index: 7325429 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1979. Min Act: -0.1700
Data Index: 6062264 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1666. Min Act: -0.1700
Data Index: 1329318 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1041. Min Act: -0.1700
Data Index: 5083109 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0728. Min Act: -0.1700
Data Index: 4711299 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.1354. Min Act: -0.1700
Data Index: 5196149 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0416. Min Act: -0.1700
Data Index: 5849616 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0728. Min Act: -0.1700
Data Index: 7582667 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0416. Min Act: -0.1700
Data Index: 1417405 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0728. Min Act: -0.1700
Data Index: 6042494 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5104. Min Range: -4.5104
Max Act: 4.0728. Min Act: -0.1700
Data Index: 1034098 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19