Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.5699. Min Act: -0.1700
Data Index: 3437382 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.3199. Min Act: -0.1700
Data Index: 2928571 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.2886. Min Act: -0.1700
Data Index: 2650845 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.2886. Min Act: -0.1700
Data Index: 6462430 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.2261. Min Act: -0.1700
Data Index: 8781144 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.2261. Min Act: -0.1700
Data Index: 8567562 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1949. Min Act: -0.1700
Data Index: 7461906 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1636. Min Act: -0.1700
Data Index: 4558306 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1636. Min Act: -0.1700
Data Index: 2710569 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1636. Min Act: -0.1700
Data Index: 2959184 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1324. Min Act: -0.1700
Data Index: 8023148 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1636. Min Act: -0.1700
Data Index: 3917628 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1324. Min Act: -0.1700
Data Index: 5559053 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1011. Min Act: -0.1700
Data Index: 6276227 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1011. Min Act: -0.1700
Data Index: 6607151 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1011. Min Act: -0.1700
Data Index: 3108922 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.1011. Min Act: -0.1700
Data Index: 8567570 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.0699. Min Act: -0.1700
Data Index: 5027873 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.0699. Min Act: -0.1700
Data Index: 5714261 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5699. Min Range: -5.5699
Max Act: 5.0699. Min Act: -0.1700
Data Index: 3536830 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19