Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.8554. Min Act: -0.1700
Data Index: 7576565 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.8241. Min Act: -0.1698
Data Index: 2163758 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.7616. Min Act: -0.1700
Data Index: 6862387 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.6366. Min Act: -0.1700
Data Index: 3422451 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.6366. Min Act: -0.1700
Data Index: 4084710 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.6054. Min Act: -0.1700
Data Index: 2105639 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.5741. Min Act: -0.1700
Data Index: 5071428 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.5429. Min Act: -0.1700
Data Index: 2346062 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.5429. Min Act: -0.1700
Data Index: 4716650 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.5429. Min Act: -0.1700
Data Index: 747426 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.5116. Min Act: -0.1700
Data Index: 1843603 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.4804. Min Act: -0.1700
Data Index: 220189 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.4804. Min Act: -0.1700
Data Index: 2506357 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.4491. Min Act: -0.1700
Data Index: 4377296 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.4179. Min Act: -0.1700
Data Index: 6896582 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.3866. Min Act: -0.1700
Data Index: 2313713 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.3866. Min Act: -0.1700
Data Index: 3205664 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.3866. Min Act: -0.1700
Data Index: 6141924 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.3866. Min Act: -0.1700
Data Index: 5508583 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8554. Min Range: -6.8554
Max Act: 6.3241. Min Act: -0.1700
Data Index: 6121314 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19