Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1685. Min Range: -4.1685
Max Act: 4.1685. Min Act: -0.1700
Data Index: 817533 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1685. Min Range: -4.1685
Max Act: 4.1060. Min Act: -0.1700
Data Index: 1948225 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1685. Min Range: -4.1685
Max Act: 4.0435. Min Act: -0.1700
Data Index: 2967945 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1685. Min Range: -4.1685
Max Act: 4.0122. Min Act: -0.1700
Data Index: 174670 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9810. Min Act: -0.1700
Data Index: 2539705 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1685. Min Range: -4.1685
Max Act: 4.0122. Min Act: -0.1700
Data Index: 1948224 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9497. Min Act: -0.1700
Data Index: 7138757 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3072751 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9184. Min Act: -0.1700
Data Index: 7045865 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9184. Min Act: -0.1700
Data Index: 5749340 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9184. Min Act: -0.1700
Data Index: 2217226 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.9184. Min Act: -0.1700
Data Index: 3909714 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8559. Min Act: -0.1700
Data Index: 5514996 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 4166972 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 141925 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8559. Min Act: -0.1700
Data Index: 2233213 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 3888597 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 6767022 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 982881 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1685. Min Range: -4.1685
Max Act: 3.8872. Min Act: -0.1700
Data Index: 938348 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19