Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3758 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.9693. Min Act: -0.1700
Data Index: 2968158 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.8583. Min Act: -0.1700
Data Index: 611483 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6989. Min Act: -0.1700
Data Index: 533628 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6989. Min Act: -0.1700
Data Index: 1595299 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6668. Min Act: -0.1700
Data Index: 3382870 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 3548099 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 574129 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 3250528 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 3579961 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 5684199 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6187. Min Act: -0.1700
Data Index: 5528410 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6187. Min Act: -0.1700
Data Index: 2915986 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 2863002 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.6026. Min Act: -0.1700
Data Index: 7079315 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 702003 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 490772 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 6888806 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 6892408 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 1468026 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9693. Min Range: -2.9693
Max Act: 2.5865. Min Act: -0.1700
Data Index: 5329658 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19