Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 2837531 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 3939838 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.3163. Min Act: -0.1700
Data Index: 772566 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.2538. Min Act: -0.1700
Data Index: 1608795 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.1288. Min Act: -0.1700
Data Index: 4059736 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.1288. Min Act: -0.1700
Data Index: 8628742 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.1288. Min Act: -0.1700
Data Index: 6030561 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0976. Min Act: -0.1700
Data Index: 6456530 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0663. Min Act: -0.1700
Data Index: 3313345 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0976. Min Act: -0.1700
Data Index: 2183765 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0351. Min Act: -0.1700
Data Index: 541963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0351. Min Act: -0.1700
Data Index: 6589929 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0663. Min Act: -0.1700
Data Index: 2842843 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0351. Min Act: -0.1700
Data Index: 5777697 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7223883 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 1229097 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 3610613 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0038. Min Act: -0.1700
Data Index: 5959406 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 2571906 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9413. Min Act: -0.1700
Data Index: 7213854 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19