Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.6932. Min Act: -0.1700
Data Index: 7143234 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5994. Min Act: -0.1700
Data Index: 4142168 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5994. Min Act: -0.1700
Data Index: 1765806 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5682. Min Act: -0.1700
Data Index: 4173977 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5369. Min Act: -0.1700
Data Index: 4146113 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5369. Min Act: -0.1700
Data Index: 256697 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5369. Min Act: -0.1700
Data Index: 6835086 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.5682. Min Act: -0.1700
Data Index: 3855335 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4432. Min Act: -0.1700
Data Index: 4848137 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4432. Min Act: -0.1700
Data Index: 6770117 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 3154302 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 4074688 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 5479043 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 8204096 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 8315231 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 8761595 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.4119. Min Act: -0.1700
Data Index: 5054345 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.3494. Min Act: -0.1700
Data Index: 2057636 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.3807. Min Act: -0.1700
Data Index: 2749300 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6932. Min Range: -7.6932
Max Act: 7.3807. Min Act: -0.1700
Data Index: 5212872 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19