Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9995. Min Act: -0.1700
Data Index: 3338368 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9682. Min Act: -0.1700
Data Index: 7633251 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4269138 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9682. Min Act: -0.1700
Data Index: 6800246 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9682. Min Act: -0.1700
Data Index: 6715367 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 4963238 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 8086646 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 7724654 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 7466517 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 7422852 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 6875962 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 5745843 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 3306352 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 4906112 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 1108937 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 3425243 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 916371 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1699
Data Index: 909644 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 807201 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9995. Min Range: -3.9995
Max Act: 3.9370. Min Act: -0.1700
Data Index: 3327740 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19