Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.8289. Min Act: -0.1700
Data Index: 2199126 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.7664. Min Act: -0.1700
Data Index: 8284095 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.7039. Min Act: -0.1700
Data Index: 1883166 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.7039. Min Act: -0.1700
Data Index: 8057769 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6726. Min Act: -0.1700
Data Index: 6151687 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6726. Min Act: -0.1700
Data Index: 5797992 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6414. Min Act: -0.1700
Data Index: 1315901 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6101. Min Act: -0.1700
Data Index: 6774341 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6414. Min Act: -0.1700
Data Index: 8123361 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6101. Min Act: -0.1700
Data Index: 563585 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6101. Min Act: -0.1700
Data Index: 8267581 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6101. Min Act: -0.1700
Data Index: 2861895 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.6101. Min Act: -0.1700
Data Index: 4673230 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4828208 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5789. Min Act: -0.1700
Data Index: 6686662 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5789. Min Act: -0.1700
Data Index: 8207067 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5789. Min Act: -0.1700
Data Index: 3620292 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5476. Min Act: -0.1700
Data Index: 5941869 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5789. Min Act: -0.1700
Data Index: 3099420 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8289. Min Range: -4.8289
Max Act: 4.5789. Min Act: -0.1700
Data Index: 5765496 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19