Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3995 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.8573. Min Act: -0.1700
Data Index: 3088197 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.5448. Min Act: -0.1700
Data Index: 7902553 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.5448. Min Act: -0.1700
Data Index: 8003795 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.4198. Min Act: -0.1700
Data Index: 767409 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3028950 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.4198. Min Act: -0.1700
Data Index: 7926486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3886. Min Act: -0.1700
Data Index: 1712274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3886. Min Act: -0.1700
Data Index: 8321723 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3886. Min Act: -0.1700
Data Index: 8574965 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3573. Min Act: -0.1700
Data Index: 6923044 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3573. Min Act: -0.1695
Data Index: 7855491 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3573. Min Act: -0.1700
Data Index: 7764409 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3573. Min Act: -0.1700
Data Index: 5148619 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 2762110 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 6391616 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 2800557 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 2821545 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 2825719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 7159566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8573. Min Range: -6.8573
Max Act: 6.3261. Min Act: -0.1700
Data Index: 6276950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19