Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.8977. Min Act: -0.1700
Data Index: 495385 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.7413. Min Act: -0.1700
Data Index: 565552 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.7413. Min Act: -0.1700
Data Index: 7147320 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.7413. Min Act: -0.1700
Data Index: 5181339 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.7100. Min Act: -0.1700
Data Index: 4293617 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.7100. Min Act: -0.1700
Data Index: 2123607 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6788. Min Act: -0.1700
Data Index: 2540117 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6788. Min Act: -0.1700
Data Index: 296959 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6788. Min Act: -0.1700
Data Index: 255171 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6788. Min Act: -0.1700
Data Index: 5394842 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6788. Min Act: -0.1700
Data Index: 1213731 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6475. Min Act: -0.1700
Data Index: 2262968 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6475. Min Act: -0.1700
Data Index: 755159 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6318. Min Act: -0.1700
Data Index: 381426 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6318. Min Act: -0.1700
Data Index: 3665528 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6162. Min Act: -0.1700
Data Index: 7103529 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6318. Min Act: -0.1700
Data Index: 3852139 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6162. Min Act: -0.1700
Data Index: 2780208 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6162. Min Act: -0.1700
Data Index: 8539680 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8977. Min Range: -3.8977
Max Act: 3.6318. Min Act: -0.1700
Data Index: 5487653 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19