Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.3922. Min Act: -0.1700
Data Index: 5664175 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.3922. Min Act: -0.1700
Data Index: 473185 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.3297. Min Act: -0.1700
Data Index: 4617146 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2672. Min Act: -0.1700
Data Index: 6342237 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2672. Min Act: -0.1700
Data Index: 681684 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2672. Min Act: -0.1700
Data Index: 3200121 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 7473303 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 5300882 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 1371093 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 7066890 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 2501612 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.2047. Min Act: -0.1700
Data Index: 1022829 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.0797. Min Act: -0.1700
Data Index: 6698940 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 6919669 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 6371864 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 163030 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 4788936 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 644687 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 7462326 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3922. Min Range: -11.3922
Max Act: 11.1422. Min Act: -0.1700
Data Index: 3106778 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19