Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.5026. Min Act: -0.1700
Data Index: 3140091 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.5026. Min Act: -0.1700
Data Index: 989050 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.4675. Min Act: -0.1700
Data Index: 7791136 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3971. Min Act: -0.1700
Data Index: 4324478 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3794. Min Act: -0.1700
Data Index: 8735713 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3618. Min Act: -0.1700
Data Index: 4808276 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3618. Min Act: -0.1700
Data Index: 2734922 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3618. Min Act: -0.1700
Data Index: 5476186 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3618. Min Act: -0.1700
Data Index: 262708 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3442. Min Act: -0.1700
Data Index: 5067976 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3442. Min Act: -0.1700
Data Index: 2127415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3265. Min Act: -0.1700
Data Index: 6250019 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3618. Min Act: -0.1700
Data Index: 6271724 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3442. Min Act: -0.1700
Data Index: 465282 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3265. Min Act: -0.1700
Data Index: 728987 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3442. Min Act: -0.1700
Data Index: 1255054 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3265. Min Act: -0.1700
Data Index: 2549332 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3265. Min Act: -0.1700
Data Index: 6512549 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3442. Min Act: -0.1700
Data Index: 6901599 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5026. Min Range: -1.5026
Max Act: 1.3265. Min Act: -0.1700
Data Index: 8586654 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19