Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1124. Min Range: -5.1124
Max Act: 5.1124. Min Act: -0.1700
Data Index: 504638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1124. Min Range: -5.1124
Max Act: 5.1124. Min Act: -0.1700
Data Index: 7068867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1124. Min Range: -5.1124
Max Act: 5.0811. Min Act: -0.1700
Data Index: 7848957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1124. Min Range: -5.1124
Max Act: 5.0186. Min Act: -0.1700
Data Index: 2536320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.9874. Min Act: -0.1700
Data Index: 4080191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.9249. Min Act: -0.1700
Data Index: 5781136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.9249. Min Act: -0.1700
Data Index: 4005158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.9249. Min Act: -0.1700
Data Index: 7619214 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8936. Min Act: -0.1700
Data Index: 6231742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8624. Min Act: -0.1700
Data Index: 7684478 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8936. Min Act: -0.1700
Data Index: 2301393 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8624. Min Act: -0.1700
Data Index: 6634247 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 7329007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 7367088 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 1129977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 239567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 7698629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 6372275 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 5570062 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1124. Min Range: -5.1124
Max Act: 4.8311. Min Act: -0.1700
Data Index: 590023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19