Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1254 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.2032. Min Act: -0.1700
Data Index: 6835337 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.2032. Min Act: -0.1700
Data Index: 5723201 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1720. Min Act: -0.1700
Data Index: 1340856 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1407. Min Act: -0.1700
Data Index: 1163031 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1407. Min Act: -0.1700
Data Index: 4071591 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 3494563 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1095. Min Act: -0.1700
Data Index: 3821218 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1407. Min Act: -0.1700
Data Index: 3646480 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4554816 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 277304 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 2682178 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0470. Min Act: -0.1700
Data Index: 1777153 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 6294175 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 1005252 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0470. Min Act: -0.1700
Data Index: 7304449 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0470. Min Act: -0.1700
Data Index: 8425529 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0782. Min Act: -0.1700
Data Index: 8456156 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0470. Min Act: -0.1700
Data Index: 4841116 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0157. Min Act: -0.1700
Data Index: 477891 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2032. Min Range: -5.2032
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5052612 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19