Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5415 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1105. Min Range: -5.1105
Max Act: 5.1105. Min Act: -0.1700
Data Index: 4066883 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1105. Min Range: -5.1105
Max Act: 5.0480. Min Act: -0.1700
Data Index: 5226365 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1105. Min Range: -5.1105
Max Act: 5.0167. Min Act: -0.1700
Data Index: 4318716 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.9542. Min Act: -0.1700
Data Index: 3619842 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6336019 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8917. Min Act: -0.1700
Data Index: 2281991 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8917. Min Act: -0.1700
Data Index: 7116224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6092838 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.9230. Min Act: -0.1700
Data Index: 834660 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8605. Min Act: -0.1700
Data Index: 7501807 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.8605. Min Act: -0.1700
Data Index: 8586802 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7980. Min Act: -0.1700
Data Index: 4059813 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7980. Min Act: -0.1700
Data Index: 8037471 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7980. Min Act: -0.1700
Data Index: 1781308 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7667. Min Act: -0.1700
Data Index: 6512086 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7667. Min Act: -0.1700
Data Index: 1024901 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7667. Min Act: -0.1700
Data Index: 2037592 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7355. Min Act: -0.1700
Data Index: 3303594 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7667. Min Act: -0.1700
Data Index: 6226537 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1105. Min Range: -5.1105
Max Act: 4.7355. Min Act: -0.1700
Data Index: 5441195 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19