Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0950. Min Act: -0.1700
Data Index: 6816612 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0950. Min Act: -0.1700
Data Index: 4885147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0950. Min Act: -0.1700
Data Index: 8199694 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0782. Min Act: -0.1700
Data Index: 3278782 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0614. Min Act: -0.1697
Data Index: 161912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0446. Min Act: -0.1700
Data Index: 6849905 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0446. Min Act: -0.1700
Data Index: 6162088 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0446. Min Act: -0.1700
Data Index: 7812513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0278. Min Act: -0.1700
Data Index: 8798245 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0109. Min Act: -0.1700
Data Index: 2054720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0446. Min Act: -0.1700
Data Index: 7067513 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0278. Min Act: -0.1700
Data Index: 2979314 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0109. Min Act: -0.1700
Data Index: 2077019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0109. Min Act: -0.1700
Data Index: 7737777 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0109. Min Act: -0.1700
Data Index: 7524061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0950. Min Range: -2.0950
Max Act: 1.9940. Min Act: -0.1700
Data Index: 553873 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0109. Min Act: -0.1700
Data Index: 6679112 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0950. Min Range: -2.0950
Max Act: 2.0278. Min Act: -0.1700
Data Index: 608521 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0950. Min Range: -2.0950
Max Act: 1.9940. Min Act: -0.1700
Data Index: 1701286 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0950. Min Range: -2.0950
Max Act: 1.9940. Min Act: -0.1700
Data Index: 4897343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19