Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.9150. Min Act: -0.1700
Data Index: 1189179 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.8213. Min Act: -0.1700
Data Index: 2324664 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.7275. Min Act: -0.1700
Data Index: 2026499 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.7275. Min Act: -0.1700
Data Index: 4224741 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.6650. Min Act: -0.1700
Data Index: 303582 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2814886 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2904825 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5713. Min Act: -0.1700
Data Index: 1912563 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5400. Min Act: -0.1700
Data Index: 1743914 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5400. Min Act: -0.1700
Data Index: 571310 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5088. Min Act: -0.1700
Data Index: 1232792 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5088. Min Act: -0.1700
Data Index: 3872301 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5088. Min Act: -0.1700
Data Index: 315444 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6510650 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4463. Min Act: -0.1700
Data Index: 571625 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6649388 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4150. Min Act: -0.1700
Data Index: 4055890 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4463. Min Act: -0.1700
Data Index: 334556 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6633737 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9150. Min Range: -5.9150
Max Act: 5.4150. Min Act: -0.1700
Data Index: 4417450 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19