Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1293 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2864695 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.1730. Min Act: -0.1700
Data Index: 7086266 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.1105. Min Act: -0.1700
Data Index: 2864692 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0480. Min Act: -0.1700
Data Index: 6765579 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0167. Min Act: -0.1700
Data Index: 7086268 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0167. Min Act: -0.1700
Data Index: 4428050 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2980. Min Range: -4.2980
Max Act: 4.0167. Min Act: -0.1700
Data Index: 6584436 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9855. Min Act: -0.1700
Data Index: 815835 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9855. Min Act: -0.1700
Data Index: 5692901 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9542. Min Act: -0.1700
Data Index: 815836 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9855. Min Act: -0.1700
Data Index: 1285273 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9542. Min Act: -0.1700
Data Index: 4602985 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 5479357 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 1039142 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 6230180 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 8206728 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 667336 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.9230. Min Act: -0.1700
Data Index: 8665475 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 2581538 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2980. Min Range: -4.2980
Max Act: 3.8604. Min Act: -0.1700
Data Index: 5058269 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19