Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1611 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2956. Min Range: -6.2956
Max Act: 6.2956. Min Act: -0.1700
Data Index: 2527881 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2956. Min Range: -6.2956
Max Act: 6.1706. Min Act: -0.1700
Data Index: 3596682 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2956. Min Range: -6.2956
Max Act: 6.1081. Min Act: -0.1700
Data Index: 6500517 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2956. Min Range: -6.2956
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7549771 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.9518. Min Act: -0.1700
Data Index: 5818206 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.9206. Min Act: -0.1700
Data Index: 8444254 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.8893. Min Act: -0.1700
Data Index: 434931 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.8581. Min Act: -0.1700
Data Index: 6373769 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.8581. Min Act: -0.1700
Data Index: 2974806 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2184798 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.8268. Min Act: -0.1700
Data Index: 3804700 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7956. Min Act: -0.1700
Data Index: 5913369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7956. Min Act: -0.1700
Data Index: 434719 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7643. Min Act: -0.1700
Data Index: 7957440 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7331. Min Act: -0.1700
Data Index: 5163008 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7331. Min Act: -0.1700
Data Index: 7674636 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7331. Min Act: -0.1700
Data Index: 8005180 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7018. Min Act: -0.1700
Data Index: 683594 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7018. Min Act: -0.1700
Data Index: 5519795 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2956. Min Range: -6.2956
Max Act: 5.7331. Min Act: -0.1700
Data Index: 6311555 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19