Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.5676. Min Act: -0.1700
Data Index: 8374970 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5421250 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.5364. Min Act: -0.1700
Data Index: 986359 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5146970 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.4114. Min Act: -0.1700
Data Index: 8706381 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2340461 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.3489. Min Act: -0.1700
Data Index: 4318436 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.3489. Min Act: -0.1700
Data Index: 858321 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.3489. Min Act: -0.1700
Data Index: 4198022 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.3176. Min Act: -0.1700
Data Index: 1949204 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2864. Min Act: -0.1700
Data Index: 5986010 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2864. Min Act: -0.1700
Data Index: 189975 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2864. Min Act: -0.1700
Data Index: 4460775 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2551. Min Act: -0.1700
Data Index: 2796861 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2551. Min Act: -0.1700
Data Index: 7934302 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.2239. Min Act: -0.1700
Data Index: 3347724 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.1926. Min Act: -0.1700
Data Index: 4110626 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.1926. Min Act: -0.1700
Data Index: 5168424 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.1926. Min Act: -0.1700
Data Index: 4519821 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5676. Min Range: -5.5676
Max Act: 5.1614. Min Act: -0.1700
Data Index: 4659066 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19