Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3956. Min Range: -1.3956
Max Act: 1.3956. Min Act: -0.1647
Data Index: 8061356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3956. Min Range: -1.3956
Max Act: 1.1137. Min Act: -0.1700
Data Index: 7820564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.9054. Min Act: -0.1581
Data Index: 2650224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7536. Min Act: -0.0858
Data Index: 351283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7289. Min Act: -0.1699
Data Index: 571786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7454. Min Act: -0.1290
Data Index: 1369023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7454. Min Act: -0.1700
Data Index: 1500473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7289. Min Act: -0.1700
Data Index: 437029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7124. Min Act: -0.1667
Data Index: 6256956 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7454. Min Act: -0.1500
Data Index: 6332559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6961. Min Act: -0.0668
Data Index: 1738455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6961. Min Act: -0.1683
Data Index: 2846342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.7043. Min Act: -0.1700
Data Index: 5206654 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6880. Min Act: -0.1687
Data Index: 853028 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6961. Min Act: -0.1700
Data Index: 5225686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6961. Min Act: -0.1681
Data Index: 3732556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6880. Min Act: -0.1699
Data Index: 476378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6798. Min Act: -0.1539
Data Index: 4685458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6717. Min Act: -0.1675
Data Index: 1866530 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3956. Min Range: -1.3956
Max Act: 0.6798. Min Act: -0.1700
Data Index: 8339462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19