Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 4054880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4574829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4613187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4360. Min Act: -0.1700
Data Index: 7680293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 4198995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 8062875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 1760079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.3733. Min Act: -0.1700
Data Index: 1729805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 3313291 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 6131063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5642551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5074312 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 111193 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.3733. Min Act: -0.1700
Data Index: 5074306 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5074305 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5074296 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 390610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 5074295 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.4046. Min Act: -0.1700
Data Index: 4397627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4360. Min Range: -3.4360
Max Act: 3.3733. Min Act: -0.1700
Data Index: 3472689 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19