Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.6042. Min Act: -0.1700
Data Index: 2220163 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.4479. Min Act: -0.1700
Data Index: 5431067 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.4167. Min Act: -0.1700
Data Index: 4495132 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.4167. Min Act: -0.1700
Data Index: 3399732 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3854. Min Act: -0.1700
Data Index: 63246 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3854. Min Act: -0.1700
Data Index: 1477567 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3854. Min Act: -0.1700
Data Index: 3890438 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3854. Min Act: -0.1700
Data Index: 7747144 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 995135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1699
Data Index: 8630644 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 5003520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3229. Min Act: -0.1700
Data Index: 3811739 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 3787915 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3229. Min Act: -0.1700
Data Index: 2781158 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3229. Min Act: -0.1700
Data Index: 7597433 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.2917. Min Act: -0.1700
Data Index: 7291110 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.2917. Min Act: -0.1700
Data Index: 2461646 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3229. Min Act: -0.1700
Data Index: 3704854 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.2917. Min Act: -0.1699
Data Index: 1572307 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.2917. Min Act: -0.1700
Data Index: 3744693 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19