Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2083. Min Range: -6.2083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 1683782 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2083. Min Range: -6.2083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 2603657 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2083. Min Range: -6.2083
Max Act: 6.1145. Min Act: -0.1700
Data Index: 8764402 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2083. Min Range: -6.2083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 8276338 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9895. Min Act: -0.1700
Data Index: 8031832 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2083. Min Range: -6.2083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 433609 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9895. Min Act: -0.1700
Data Index: 2607218 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9583. Min Act: -0.1700
Data Index: 976318 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 7840851 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 5711411 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 4061163 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 688532 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 1068029 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8958. Min Act: -0.1700
Data Index: 6807298 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8958. Min Act: -0.1700
Data Index: 1233507 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8958. Min Act: -0.1700
Data Index: 1777191 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3956858 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8645. Min Act: -0.1700
Data Index: 3208815 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.9270. Min Act: -0.1700
Data Index: 3044555 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2083. Min Range: -6.2083
Max Act: 5.8958. Min Act: -0.1700
Data Index: 7501115 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19