Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4707 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.3011. Min Act: -0.1700
Data Index: 414636 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.2386. Min Act: -0.1700
Data Index: 2250183 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1448. Min Act: -0.1700
Data Index: 6848322 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.1136. Min Act: -0.1700
Data Index: 4859629 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0511. Min Act: -0.1700
Data Index: 5218957 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0511. Min Act: -0.1700
Data Index: 5845627 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0198. Min Act: -0.1700
Data Index: 4725560 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0198. Min Act: -0.1700
Data Index: 2187383 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3011. Min Range: -6.3011
Max Act: 6.0198. Min Act: -0.1700
Data Index: 5176187 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4255391 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 4948244 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 1094531 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 6432639 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 1856777 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3201625 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 5964251 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 7497778 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 2423709 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9886. Min Act: -0.1700
Data Index: 8795746 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3011. Min Range: -6.3011
Max Act: 5.9573. Min Act: -0.1700
Data Index: 5675001 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19