Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 459 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.3695. Min Act: -0.1700
Data Index: 320423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5611518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2758. Min Act: -0.1700
Data Index: 5170391 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2445. Min Act: -0.1700
Data Index: 1343752 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2445. Min Act: -0.1700
Data Index: 1977400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2445. Min Act: -0.1700
Data Index: 6994903 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 4562697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 4675913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 4710477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 7406959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 7174977 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 6064396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 6291091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1820. Min Act: -0.1700
Data Index: 2249015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1820. Min Act: -0.1700
Data Index: 6379901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1507. Min Act: -0.1700
Data Index: 5587266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.2133. Min Act: -0.1700
Data Index: 3046054 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1820. Min Act: -0.1700
Data Index: 2041222 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1820. Min Act: -0.1700
Data Index: 2075086 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3695. Min Range: -4.3695
Max Act: 4.1820. Min Act: -0.1700
Data Index: 3844403 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19