Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.1113. Min Act: -0.1700
Data Index: 611276 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1697
Data Index: 835896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 343168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 1725819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 6971897 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 5468497 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 320463 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 8188232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1113. Min Range: -2.1113
Max Act: 2.0105. Min Act: -0.1700
Data Index: 7787993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9766. Min Act: -0.1700
Data Index: 6659299 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9766. Min Act: -0.1700
Data Index: 827503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9766. Min Act: -0.1700
Data Index: 2806843 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9427. Min Act: -0.1700
Data Index: 3094620 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9597. Min Act: -0.1700
Data Index: 5865308 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9597. Min Act: -0.1700
Data Index: 1046969 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9427. Min Act: -0.1700
Data Index: 3580889 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9427. Min Act: -0.1700
Data Index: 1833505 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9087. Min Act: -0.1695
Data Index: 4429202 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9257. Min Act: -0.1700
Data Index: 7188247 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1113. Min Range: -2.1113
Max Act: 1.9087. Min Act: -0.1700
Data Index: 6990713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19