Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1638. Min Range: -5.1638
Max Act: 5.1638. Min Act: -0.1700
Data Index: 1544938 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1638. Min Range: -5.1638
Max Act: 5.0388. Min Act: -0.1700
Data Index: 4605902 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1638. Min Range: -5.1638
Max Act: 5.0700. Min Act: -0.1700
Data Index: 5704189 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1638. Min Range: -5.1638
Max Act: 5.0388. Min Act: -0.1700
Data Index: 3459145 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.9138. Min Act: -0.1700
Data Index: 5476384 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.9138. Min Act: -0.1700
Data Index: 7829851 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8825. Min Act: -0.1700
Data Index: 558290 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8825. Min Act: -0.1700
Data Index: 558291 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8825. Min Act: -0.1700
Data Index: 3038622 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8513. Min Act: -0.1700
Data Index: 2285794 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8825. Min Act: -0.1700
Data Index: 2880464 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8200. Min Act: -0.1700
Data Index: 4099511 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8513. Min Act: -0.1700
Data Index: 1242095 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8513. Min Act: -0.1700
Data Index: 3459146 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8825. Min Act: -0.1700
Data Index: 919826 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8513. Min Act: -0.1700
Data Index: 690779 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.7888. Min Act: -0.1700
Data Index: 1270080 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8200. Min Act: -0.1700
Data Index: 1694138 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8200. Min Act: -0.1700
Data Index: 1441458 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1638. Min Range: -5.1638
Max Act: 4.8200. Min Act: -0.1700
Data Index: 6845518 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19