Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1007. Min Range: -8.1007
Max Act: 8.1007. Min Act: -0.1700
Data Index: 4849840 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.8507. Min Act: -0.1700
Data Index: 237665 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.7882. Min Act: -0.1700
Data Index: 7553188 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.7882. Min Act: -0.1700
Data Index: 2388552 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.7257. Min Act: -0.1700
Data Index: 1581561 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6945. Min Act: -0.1700
Data Index: 1713296 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6945. Min Act: -0.1700
Data Index: 2583686 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6320. Min Act: -0.1700
Data Index: 4778605 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6007. Min Act: -0.1700
Data Index: 2729776 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6320. Min Act: -0.1700
Data Index: 4652047 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6007. Min Act: -0.1700
Data Index: 1009332 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6632. Min Act: -0.1700
Data Index: 108559 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6320. Min Act: -0.1700
Data Index: 8064485 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6007. Min Act: -0.1700
Data Index: 5456612 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6320. Min Act: -0.1700
Data Index: 7572930 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.6007. Min Act: -0.1700
Data Index: 105755 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.5695. Min Act: -0.1700
Data Index: 341982 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.5695. Min Act: -0.1700
Data Index: 4439281 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.5382. Min Act: -0.1700
Data Index: 3193105 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.5070. Min Act: -0.1700
Data Index: 1331205 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19