Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 300 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2202. Min Range: -5.2202
Max Act: 5.2202. Min Act: -0.1700
Data Index: 7018527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2202. Min Range: -5.2202
Max Act: 5.0952. Min Act: -0.1700
Data Index: 7687091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2202. Min Range: -5.2202
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2941639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.8139. Min Act: -0.1700
Data Index: 2759253 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.8139. Min Act: -0.1700
Data Index: 2869242 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3219940 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.8139. Min Act: -0.1700
Data Index: 8655097 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.8139. Min Act: -0.1700
Data Index: 1345123 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7827. Min Act: -0.1700
Data Index: 3512649 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7827. Min Act: -0.1700
Data Index: 1249014 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7514. Min Act: -0.1700
Data Index: 2682063 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7202. Min Act: -0.1700
Data Index: 5407680 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7514. Min Act: -0.1700
Data Index: 3263093 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7202. Min Act: -0.1700
Data Index: 7021046 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7514. Min Act: -0.1700
Data Index: 2221577 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.6889. Min Act: -0.1700
Data Index: 7413771 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7202. Min Act: -0.1700
Data Index: 4691375 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.6889. Min Act: -0.1700
Data Index: 7392360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.6889. Min Act: -0.1700
Data Index: 1980312 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2202. Min Range: -5.2202
Max Act: 4.7202. Min Act: -0.1700
Data Index: 3967295 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19