Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3119 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1312. Min Range: -5.1312
Max Act: 5.1312. Min Act: -0.1700
Data Index: 4946871 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.9437. Min Act: -0.1700
Data Index: 2279372 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7874. Min Act: -0.1700
Data Index: 5701890 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7874. Min Act: -0.1700
Data Index: 7222974 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1764945 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.8187. Min Act: -0.1700
Data Index: 7689930 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1937121 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7562. Min Act: -0.1700
Data Index: 3437817 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7249. Min Act: -0.1700
Data Index: 1298428 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7249. Min Act: -0.1700
Data Index: 3310931 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7249. Min Act: -0.1700
Data Index: 5470664 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6937. Min Act: -0.1700
Data Index: 2473207 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.7249. Min Act: -0.1700
Data Index: 5445175 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6937. Min Act: -0.1700
Data Index: 4751459 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6937. Min Act: -0.1700
Data Index: 4459341 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6624. Min Act: -0.1700
Data Index: 2396103 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6624. Min Act: -0.1700
Data Index: 4924358 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6312. Min Act: -0.1700
Data Index: 7689759 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.6312. Min Act: -0.1700
Data Index: 7528973 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1312. Min Range: -5.1312
Max Act: 4.5687. Min Act: -0.1700
Data Index: 1956273 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19