Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.8538. Min Act: -0.1700
Data Index: 3568299 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.8284. Min Act: -0.1700
Data Index: 3404089 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.8200. Min Act: -0.1700
Data Index: 583384 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.8115. Min Act: -0.1700
Data Index: 7778108 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.8031. Min Act: -0.1700
Data Index: 2563006 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7697. Min Act: -0.1697
Data Index: 7959688 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7697. Min Act: -0.1700
Data Index: 5712496 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7697. Min Act: -0.1700
Data Index: 3959069 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7780. Min Act: -0.1700
Data Index: 6114255 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7614. Min Act: -0.1700
Data Index: 932861 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7614. Min Act: -0.1700
Data Index: 3919721 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7614. Min Act: -0.1700
Data Index: 4640642 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7531. Min Act: -0.1700
Data Index: 4885280 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7614. Min Act: -0.1700
Data Index: 1996111 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7448. Min Act: -0.1700
Data Index: 6532567 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7448. Min Act: -0.1700
Data Index: 8051808 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7531. Min Act: -0.1700
Data Index: 7867870 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7531. Min Act: -0.1700
Data Index: 1488591 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7614. Min Act: -0.1700
Data Index: 2080051 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8538. Min Range: -0.8538
Max Act: 0.7448. Min Act: -0.1700
Data Index: 5767152 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19