Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.8572. Min Act: -0.1700
Data Index: 7475029 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.7947. Min Act: -0.1700
Data Index: 7771822 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.6072. Min Act: -0.1700
Data Index: 4283643 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.6072. Min Act: -0.1700
Data Index: 5551141 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.5447. Min Act: -0.1700
Data Index: 2237770 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4822. Min Act: -0.1700
Data Index: 8215052 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4822. Min Act: -0.1700
Data Index: 1085594 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 2360648 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 6727550 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 3666532 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 2324913 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 5551144 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 7953155 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.3259. Min Act: -0.1700
Data Index: 6988786 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.3572. Min Act: -0.1700
Data Index: 6475574 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.4197. Min Act: -0.1700
Data Index: 6398122 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.3572. Min Act: -0.1700
Data Index: 6468422 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.3259. Min Act: -0.1700
Data Index: 2194864 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.3572. Min Act: -0.1700
Data Index: 6567331 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8572. Min Range: -8.8572
Max Act: 8.2947. Min Act: -0.1700
Data Index: 7470671 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19