Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 487 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3932. Min Act: -0.1700
Data Index: 1473950 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3668. Min Act: -0.1700
Data Index: 8813121 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3491. Min Act: -0.1700
Data Index: 2228934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3491. Min Act: -0.1700
Data Index: 244570 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3403. Min Act: -0.1700
Data Index: 3584280 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3403. Min Act: -0.1700
Data Index: 3738698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1700
Data Index: 7527442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3227. Min Act: -0.1700
Data Index: 8561406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3403. Min Act: -0.1700
Data Index: 5137131 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1700
Data Index: 3418163 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1700
Data Index: 2443555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3227. Min Act: -0.1700
Data Index: 866239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1699
Data Index: 1308646 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1700
Data Index: 5564387 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3315. Min Act: -0.1699
Data Index: 1678493 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3139. Min Act: -0.1700
Data Index: 7788350 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3139. Min Act: -0.1700
Data Index: 6332717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3227. Min Act: -0.1700
Data Index: 5919764 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3227. Min Act: -0.1700
Data Index: 5348983 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3932. Min Range: -1.3932
Max Act: 1.3139. Min Act: -0.1700
Data Index: 7632383 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19