Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.9900. Min Act: -0.1700
Data Index: 8258018 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.9588. Min Act: -0.1700
Data Index: 7263339 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8650. Min Act: -0.1700
Data Index: 4354445 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8650. Min Act: -0.1700
Data Index: 732259 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8338. Min Act: -0.1700
Data Index: 2557838 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8338. Min Act: -0.1700
Data Index: 7613983 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8025. Min Act: -0.1700
Data Index: 2734653 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8338. Min Act: -0.1700
Data Index: 4680207 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.8338. Min Act: -0.1700
Data Index: 3621885 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7713. Min Act: -0.1700
Data Index: 5642858 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 8009622 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 2832189 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7713. Min Act: -0.1700
Data Index: 6849422 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 1656054 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 7263346 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7713. Min Act: -0.1700
Data Index: 2900243 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 248688 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 996755 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7400. Min Act: -0.1700
Data Index: 6667525 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9900. Min Range: -4.9900
Max Act: 4.7088. Min Act: -0.1700
Data Index: 3373382 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19