Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0548. Min Range: -4.0548
Max Act: 4.0548. Min Act: -0.1700
Data Index: 6797538 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.9923. Min Act: -0.1700
Data Index: 6964950 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0548. Min Range: -4.0548
Max Act: 4.0236. Min Act: -0.1700
Data Index: 5438609 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.9298. Min Act: -0.1700
Data Index: 6117967 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.8985. Min Act: -0.1700
Data Index: 3568611 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7735. Min Act: -0.1700
Data Index: 8167878 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.8360. Min Act: -0.1700
Data Index: 8052421 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.8360. Min Act: -0.1700
Data Index: 1355138 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.8360. Min Act: -0.1700
Data Index: 8738532 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7422. Min Act: -0.1700
Data Index: 2036012 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7735. Min Act: -0.1700
Data Index: 2953279 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7109. Min Act: -0.1700
Data Index: 6847737 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7735. Min Act: -0.1700
Data Index: 5093448 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7735. Min Act: -0.1700
Data Index: 7071604 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7422. Min Act: -0.1700
Data Index: 1286536 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7109. Min Act: -0.1700
Data Index: 7485185 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7422. Min Act: -0.1700
Data Index: 5471856 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7109. Min Act: -0.1700
Data Index: 7395774 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7422. Min Act: -0.1700
Data Index: 2990308 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0548. Min Range: -4.0548
Max Act: 3.7109. Min Act: -0.1700
Data Index: 4166836 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19