Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0140. Min Range: -5.0140
Max Act: 5.0140. Min Act: -0.1700
Data Index: 450250 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9828. Min Act: -0.1700
Data Index: 19667 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 4327999 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 450249 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 7852809 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9203. Min Act: -0.1700
Data Index: 5329921 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.9203. Min Act: -0.1700
Data Index: 199773 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.8890. Min Act: -0.1700
Data Index: 6333845 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.8890. Min Act: -0.1700
Data Index: 4780060 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.8265. Min Act: -0.1700
Data Index: 6333847 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.8265. Min Act: -0.1700
Data Index: 6650784 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7953. Min Act: -0.1700
Data Index: 2503239 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7953. Min Act: -0.1700
Data Index: 2313888 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7328. Min Act: -0.1700
Data Index: 2492122 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7640. Min Act: -0.1700
Data Index: 996974 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7640. Min Act: -0.1700
Data Index: 5675753 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7640. Min Act: -0.1700
Data Index: 3452056 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7640. Min Act: -0.1700
Data Index: 3057281 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5563817 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0140. Min Range: -5.0140
Max Act: 4.6703. Min Act: -0.1700
Data Index: 5061966 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19