Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.8844. Min Act: -0.1700
Data Index: 3818038 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.7594. Min Act: -0.1700
Data Index: 2827887 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.7594. Min Act: -0.1700
Data Index: 3818034 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.6344. Min Act: -0.1700
Data Index: 4161497 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.6344. Min Act: -0.1700
Data Index: 7784768 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.6344. Min Act: -0.1700
Data Index: 6182099 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.6344. Min Act: -0.1700
Data Index: 7638623 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.6031. Min Act: -0.1700
Data Index: 219013 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7638625 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.4156. Min Act: -0.1700
Data Index: 6990025 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.4156. Min Act: -0.1700
Data Index: 1033287 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 1543506 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.4156. Min Act: -0.1700
Data Index: 4825120 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 2335796 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 188318 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 2210864 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 358125 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 6310384 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3531. Min Act: -0.1700
Data Index: 390844 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8844. Min Range: -6.8844
Max Act: 6.3219. Min Act: -0.1700
Data Index: 611860 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19