Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.4147. Min Act: -0.1700
Data Index: 3977558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.4059. Min Act: -0.1700
Data Index: 6909957 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3619. Min Act: -0.1700
Data Index: 8555300 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3619. Min Act: -0.1700
Data Index: 4184872 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3531. Min Act: -0.1700
Data Index: 5040948 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3354. Min Act: -0.1700
Data Index: 5496950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3531. Min Act: -0.1700
Data Index: 6201296 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3531. Min Act: -0.1700
Data Index: 4587366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3442. Min Act: -0.1700
Data Index: 8266592 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3354. Min Act: -0.1700
Data Index: 6933558 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3266. Min Act: -0.1700
Data Index: 2832357 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3266. Min Act: -0.1700
Data Index: 600711 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3266. Min Act: -0.1700
Data Index: 7388372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3266. Min Act: -0.1700
Data Index: 4322903 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3266. Min Act: -0.1700
Data Index: 3460560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3178. Min Act: -0.1700
Data Index: 5644585 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3354. Min Act: -0.1700
Data Index: 3172729 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3178. Min Act: -0.1700
Data Index: 6548576 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3178. Min Act: -0.1700
Data Index: 4423378 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4147. Min Range: -1.4147
Max Act: 1.3090. Min Act: -0.1700
Data Index: 7575105 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19