Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4699. Min Act: -0.1700
Data Index: 7442848 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.4387. Min Act: -0.1700
Data Index: 843696 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 2215634 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 6979162 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3449. Min Act: -0.1700
Data Index: 2155460 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2824. Min Act: -0.1700
Data Index: 166119 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.3137. Min Act: -0.1700
Data Index: 4360260 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2824. Min Act: -0.1700
Data Index: 6038768 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2512. Min Act: -0.1700
Data Index: 4514237 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.2199. Min Act: -0.1700
Data Index: 5848319 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 2058361 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 6141878 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1574. Min Act: -0.1700
Data Index: 988189 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 8164724 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1574. Min Act: -0.1700
Data Index: 4316241 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 1510903 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 5771716 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 5724028 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1887. Min Act: -0.1700
Data Index: 5139779 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4699. Min Range: -4.4699
Max Act: 4.1574. Min Act: -0.1700
Data Index: 1573722 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19