Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0621. Min Range: -2.0621
Max Act: 2.0621. Min Act: -0.1700
Data Index: 172766 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0621. Min Range: -2.0621
Max Act: 2.0452. Min Act: -0.1700
Data Index: 172769 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0621. Min Range: -2.0621
Max Act: 2.0452. Min Act: -0.1700
Data Index: 546304 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0621. Min Range: -2.0621
Max Act: 2.0115. Min Act: -0.1700
Data Index: 172765 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9946. Min Act: -0.1700
Data Index: 172770 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9946. Min Act: -0.1700
Data Index: 4449572 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9946. Min Act: -0.1700
Data Index: 6806351 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 917645 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 676175 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 7693953 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 172767 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 7080447 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 1620026 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 3445736 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 172768 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9777. Min Act: -0.1700
Data Index: 5011084 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9608. Min Act: -0.1700
Data Index: 4018508 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9608. Min Act: -0.1700
Data Index: 3357228 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9608. Min Act: -0.1700
Data Index: 8491711 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0621. Min Range: -2.0621
Max Act: 1.9608. Min Act: -0.1700
Data Index: 1595755 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19