Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0519. Min Act: -0.1700
Data Index: 7910961 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0687. Min Act: -0.1700
Data Index: 94811 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0351. Min Act: -0.1700
Data Index: 3652654 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0519. Min Act: -0.1700
Data Index: 5369225 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0351. Min Act: -0.1700
Data Index: 4805513 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0519. Min Act: -0.1700
Data Index: 543978 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0519. Min Act: -0.1700
Data Index: 5364383 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0351. Min Act: -0.1700
Data Index: 1767356 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0013. Min Act: -0.1700
Data Index: 4840117 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0687. Min Range: -2.0687
Max Act: 2.0182. Min Act: -0.1700
Data Index: 6270306 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 7268263 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 7532826 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 2590335 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 253536 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 7395913 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 2375585 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9675. Min Act: -0.1700
Data Index: 295666 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9675. Min Act: -0.1700
Data Index: 2643411 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9844. Min Act: -0.1700
Data Index: 5635611 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0687. Min Range: -2.0687
Max Act: 1.9675. Min Act: -0.1700
Data Index: 524003 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19