Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.4098. Min Act: -0.1700
Data Index: 1749261 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2848. Min Act: -0.1700
Data Index: 2191391 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1286. Min Act: -0.1700
Data Index: 1639031 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1286. Min Act: -0.1700
Data Index: 6966801 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0661. Min Act: -0.1700
Data Index: 3592143 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0973. Min Act: -0.1700
Data Index: 7346941 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0661. Min Act: -0.1700
Data Index: 15502 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0036. Min Act: -0.1700
Data Index: 4816559 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0348. Min Act: -0.1700
Data Index: 1105925 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0036. Min Act: -0.1700
Data Index: 4707087 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9723. Min Act: -0.1700
Data Index: 7214014 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9723. Min Act: -0.1700
Data Index: 6419839 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9411. Min Act: -0.1700
Data Index: 6313267 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9411. Min Act: -0.1700
Data Index: 5307634 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9411. Min Act: -0.1700
Data Index: 8523023 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9411. Min Act: -0.1700
Data Index: 3876237 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.9098. Min Act: -0.1700
Data Index: 6876278 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.8786. Min Act: -0.1700
Data Index: 1028402 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.8786. Min Act: -0.1700
Data Index: 5051718 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4098. Min Range: -6.4098
Max Act: 5.8786. Min Act: -0.1700
Data Index: 7323983 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19